< Prev | Home | Model | Random | Next >

Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1361 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')



Text #0

Max Range: 6.8020. Min Range: -6.8020

Max Act: 6.8020. Min Act: -0.1700

Data Index: 833307 (C4 (Web Text))

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 6.8020. Min Range: -6.8020

Max Act: 6.3957. Min Act: -0.1700

Data Index: 376039 (C4 (Web Text))

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 6.8020. Min Range: -6.8020

Max Act: 6.3645. Min Act: -0.1700

Data Index: 1489674 (Python Code)

Max Activating Token Index: 520

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 6.8020. Min Range: -6.8020

Max Act: 6.3020. Min Act: -0.1700

Data Index: 396436 (C4 (Web Text))

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 6.8020. Min Range: -6.8020

Max Act: 6.2395. Min Act: -0.1700

Data Index: 70526 (C4 (Web Text))

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 6.8020. Min Range: -6.8020

Max Act: 6.1770. Min Act: -0.1700

Data Index: 1503361 (Python Code)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 6.8020. Min Range: -6.8020

Max Act: 6.1770. Min Act: -0.1700

Data Index: 20325 (C4 (Web Text))

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 6.8020. Min Range: -6.8020

Max Act: 6.0207. Min Act: -0.1700

Data Index: 638597 (C4 (Web Text))

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 6.8020. Min Range: -6.8020

Max Act: 6.0207. Min Act: -0.1700

Data Index: 783596 (C4 (Web Text))

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 6.8020. Min Range: -6.8020

Max Act: 6.0832. Min Act: -0.1700

Data Index: 784203 (C4 (Web Text))

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 6.8020. Min Range: -6.8020

Max Act: 6.0207. Min Act: -0.1700

Data Index: 1286947 (C4 (Web Text))

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 6.8020. Min Range: -6.8020

Max Act: 5.9582. Min Act: -0.1700

Data Index: 1231970 (C4 (Web Text))

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 6.8020. Min Range: -6.8020

Max Act: 5.9582. Min Act: -0.1700

Data Index: 756909 (C4 (Web Text))

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 6.8020. Min Range: -6.8020

Max Act: 5.7707. Min Act: -0.1700

Data Index: 1160738 (C4 (Web Text))

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 6.8020. Min Range: -6.8020

Max Act: 5.8957. Min Act: -0.1700

Data Index: 1221689 (C4 (Web Text))

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 6.8020. Min Range: -6.8020

Max Act: 5.8020. Min Act: -0.1700

Data Index: 1193365 (C4 (Web Text))

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 6.8020. Min Range: -6.8020

Max Act: 5.6145. Min Act: -0.1700

Data Index: 1614525 (Python Code)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 6.8020. Min Range: -6.8020

Max Act: 5.6145. Min Act: -0.1700

Data Index: 849006 (C4 (Web Text))

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 6.8020. Min Range: -6.8020

Max Act: 5.5520. Min Act: -0.1700

Data Index: 888259 (C4 (Web Text))

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 6.8020. Min Range: -6.8020

Max Act: 5.5520. Min Act: -0.1700

Data Index: 1088499 (C4 (Web Text))

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #19