< Prev | Home | Model | Random | Next >

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

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

Neuron 875 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 6.5425. Min Range: -6.5425

Max Act: 6.5425. Min Act: -0.1699

Data Index: 484012 (C4 (Web Text))

Max Activating Token Index: 900

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 6.5425. Min Range: -6.5425

Max Act: 6.4488. Min Act: -0.1700

Data Index: 205842 (C4 (Web Text))

Max Activating Token Index: 371

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 6.5425. Min Range: -6.5425

Max Act: 6.3863. Min Act: -0.1700

Data Index: 989404 (C4 (Web Text))

Max Activating Token Index: 216

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 6.5425. Min Range: -6.5425

Max Act: 6.1988. Min Act: -0.1700

Data Index: 761422 (C4 (Web Text))

Max Activating Token Index: 315

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 6.5425. Min Range: -6.5425

Max Act: 6.1363. Min Act: -0.1700

Data Index: 1440995 (Python Code)

Max Activating Token Index: 832

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 6.5425. Min Range: -6.5425

Max Act: 6.0425. Min Act: -0.1700

Data Index: 1433202 (Python Code)

Max Activating Token Index: 257

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 6.5425. Min Range: -6.5425

Max Act: 6.1050. Min Act: -0.1700

Data Index: 309329 (C4 (Web Text))

Max Activating Token Index: 879

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 6.5425. Min Range: -6.5425

Max Act: 6.0113. Min Act: -0.1700

Data Index: 912382 (C4 (Web Text))

Max Activating Token Index: 1021

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 6.5425. Min Range: -6.5425

Max Act: 6.0113. Min Act: -0.1700

Data Index: 105802 (C4 (Web Text))

Max Activating Token Index: 573

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 6.5425. Min Range: -6.5425

Max Act: 6.0113. Min Act: -0.1700

Data Index: 1613494 (Python Code)

Max Activating Token Index: 861

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 6.5425. Min Range: -6.5425

Max Act: 5.9800. Min Act: -0.1700

Data Index: 1286038 (C4 (Web Text))

Max Activating Token Index: 826

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 6.5425. Min Range: -6.5425

Max Act: 5.9800. Min Act: -0.1699

Data Index: 519381 (C4 (Web Text))

Max Activating Token Index: 604

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 6.5425. Min Range: -6.5425

Max Act: 5.9488. Min Act: -0.1700

Data Index: 461335 (C4 (Web Text))

Max Activating Token Index: 83

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 6.5425. Min Range: -6.5425

Max Act: 6.0113. Min Act: -0.1700

Data Index: 846134 (C4 (Web Text))

Max Activating Token Index: 952

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 6.5425. Min Range: -6.5425

Max Act: 6.0425. Min Act: -0.1700

Data Index: 762121 (C4 (Web Text))

Max Activating Token Index: 342

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 6.5425. Min Range: -6.5425

Max Act: 5.9175. Min Act: -0.1700

Data Index: 182143 (C4 (Web Text))

Max Activating Token Index: 865

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 6.5425. Min Range: -6.5425

Max Act: 5.9175. Min Act: -0.1665

Data Index: 1224070 (C4 (Web Text))

Max Activating Token Index: 231

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 6.5425. Min Range: -6.5425

Max Act: 5.8550. Min Act: -0.1700

Data Index: 456516 (C4 (Web Text))

Max Activating Token Index: 457

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 6.5425. Min Range: -6.5425

Max Act: 5.8863. Min Act: -0.1700

Data Index: 1037952 (C4 (Web Text))

Max Activating Token Index: 653

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 6.5425. Min Range: -6.5425

Max Act: 5.9175. Min Act: -0.1700

Data Index: 351763 (C4 (Web Text))

Max Activating Token Index: 288

Click toggle to see full text

Truncated

Full Text #19