< Prev | Home | Model | Random | Next >

Model: GELU Model: 3 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 549 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')



Text #0

Max Range: 2.9111. Min Range: -2.9111

Max Act: 2.9111. Min Act: -0.1700

Data Index: 1080853 (C4 (Web Text))

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.9111. Min Range: -2.9111

Max Act: 2.8476. Min Act: -0.1700

Data Index: 1489874 (Python Code)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.9111. Min Range: -2.9111

Max Act: 2.8476. Min Act: -0.1700

Data Index: 1225213 (C4 (Web Text))

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.9111. Min Range: -2.9111

Max Act: 2.8158. Min Act: -0.1700

Data Index: 499235 (C4 (Web Text))

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.9111. Min Range: -2.9111

Max Act: 2.7840. Min Act: -0.1700

Data Index: 567761 (C4 (Web Text))

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.9111. Min Range: -2.9111

Max Act: 2.7680. Min Act: -0.1700

Data Index: 439747 (C4 (Web Text))

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.9111. Min Range: -2.9111

Max Act: 2.7521. Min Act: -0.1700

Data Index: 851304 (C4 (Web Text))

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.9111. Min Range: -2.9111

Max Act: 2.7521. Min Act: -0.1700

Data Index: 140084 (C4 (Web Text))

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.9111. Min Range: -2.9111

Max Act: 2.7840. Min Act: -0.1700

Data Index: 198876 (C4 (Web Text))

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.9111. Min Range: -2.9111

Max Act: 2.7680. Min Act: -0.1700

Data Index: 524740 (C4 (Web Text))

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.9111. Min Range: -2.9111

Max Act: 2.7201. Min Act: -0.1700

Data Index: 367487 (C4 (Web Text))

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.9111. Min Range: -2.9111

Max Act: 2.7680. Min Act: -0.1700

Data Index: 1115568 (C4 (Web Text))

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.9111. Min Range: -2.9111

Max Act: 2.7201. Min Act: -0.1700

Data Index: 667110 (C4 (Web Text))

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.9111. Min Range: -2.9111

Max Act: 2.7201. Min Act: -0.1700

Data Index: 1320687 (C4 (Web Text))

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.9111. Min Range: -2.9111

Max Act: 2.7201. Min Act: -0.1700

Data Index: 1635563 (Python Code)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.9111. Min Range: -2.9111

Max Act: 2.7201. Min Act: -0.1700

Data Index: 595200 (C4 (Web Text))

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.9111. Min Range: -2.9111

Max Act: 2.7041. Min Act: -0.1700

Data Index: 1012893 (C4 (Web Text))

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.9111. Min Range: -2.9111

Max Act: 2.7201. Min Act: -0.1700

Data Index: 295421 (C4 (Web Text))

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.9111. Min Range: -2.9111

Max Act: 2.7361. Min Act: -0.1700

Data Index: 1228033 (C4 (Web Text))

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.9111. Min Range: -2.9111

Max Act: 2.7041. Min Act: -0.1700

Data Index: 506954 (C4 (Web Text))

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #19