< Prev | Home | Model | Random | Next >

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

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

Neuron 354 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 2.8445. Min Range: -2.8445

Max Act: 2.8445. Min Act: -0.1700

Data Index: 699599 (C4 (Web Text))

Max Activating Token Index: 46

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.8445. Min Range: -2.8445

Max Act: 2.7968. Min Act: -0.1700

Data Index: 996619 (C4 (Web Text))

Max Activating Token Index: 10

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.8445. Min Range: -2.8445

Max Act: 2.8127. Min Act: -0.1700

Data Index: 438890 (C4 (Web Text))

Max Activating Token Index: 147

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.8445. Min Range: -2.8445

Max Act: 2.8286. Min Act: -0.1700

Data Index: 784936 (C4 (Web Text))

Max Activating Token Index: 844

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.8445. Min Range: -2.8445

Max Act: 2.7968. Min Act: -0.1700

Data Index: 1310891 (C4 (Web Text))

Max Activating Token Index: 11

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.8445. Min Range: -2.8445

Max Act: 2.7968. Min Act: -0.1700

Data Index: 285108 (C4 (Web Text))

Max Activating Token Index: 30

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.8445. Min Range: -2.8445

Max Act: 2.7809. Min Act: -0.1700

Data Index: 646308 (C4 (Web Text))

Max Activating Token Index: 426

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.8445. Min Range: -2.8445

Max Act: 2.7649. Min Act: -0.1700

Data Index: 1109529 (C4 (Web Text))

Max Activating Token Index: 455

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.8445. Min Range: -2.8445

Max Act: 2.7809. Min Act: -0.1700

Data Index: 973403 (C4 (Web Text))

Max Activating Token Index: 71

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.8445. Min Range: -2.8445

Max Act: 2.7649. Min Act: -0.1700

Data Index: 691884 (C4 (Web Text))

Max Activating Token Index: 651

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.8445. Min Range: -2.8445

Max Act: 2.7490. Min Act: -0.1700

Data Index: 1383255 (Python Code)

Max Activating Token Index: 675

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.8445. Min Range: -2.8445

Max Act: 2.7490. Min Act: -0.1700

Data Index: 1426245 (Python Code)

Max Activating Token Index: 533

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.8445. Min Range: -2.8445

Max Act: 2.7649. Min Act: -0.1700

Data Index: 437419 (C4 (Web Text))

Max Activating Token Index: 532

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.8445. Min Range: -2.8445

Max Act: 2.7649. Min Act: -0.1700

Data Index: 537732 (C4 (Web Text))

Max Activating Token Index: 3

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.8445. Min Range: -2.8445

Max Act: 2.7490. Min Act: -0.1700

Data Index: 259506 (C4 (Web Text))

Max Activating Token Index: 10

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.8445. Min Range: -2.8445

Max Act: 2.7330. Min Act: -0.1700

Data Index: 1056774 (C4 (Web Text))

Max Activating Token Index: 11

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.8445. Min Range: -2.8445

Max Act: 2.7330. Min Act: -0.1700

Data Index: 110323 (C4 (Web Text))

Max Activating Token Index: 18

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.8445. Min Range: -2.8445

Max Act: 2.7490. Min Act: -0.1700

Data Index: 1349258 (C4 (Web Text))

Max Activating Token Index: 27

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.8445. Min Range: -2.8445

Max Act: 2.7490. Min Act: -0.1700

Data Index: 957580 (C4 (Web Text))

Max Activating Token Index: 535

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.8445. Min Range: -2.8445

Max Act: 2.7490. Min Act: -0.1700

Data Index: 900551 (C4 (Web Text))

Max Activating Token Index: 920

Click toggle to see full text

Truncated

Full Text #19