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

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

Neuron 519 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: 7.8226. Min Range: -7.8226

Max Act: 7.8226. Min Act: -0.1700

Data Index: 1217867 (C4 (Web Text))

Max Activating Token Index: 549

Text #1

Max Range: 7.8226. Min Range: -7.8226

Max Act: 7.7288. Min Act: -0.1700

Data Index: 371461 (C4 (Web Text))

Max Activating Token Index: 549

Text #2

Max Range: 7.8226. Min Range: -7.8226

Max Act: 7.5101. Min Act: -0.1700

Data Index: 153799 (C4 (Web Text))

Max Activating Token Index: 861

Text #3

Max Range: 7.8226. Min Range: -7.8226

Max Act: 7.4476. Min Act: -0.1700

Data Index: 1204424 (C4 (Web Text))

Max Activating Token Index: 668

Text #4

Max Range: 7.8226. Min Range: -7.8226

Max Act: 7.3538. Min Act: -0.1700

Data Index: 90442 (C4 (Web Text))

Max Activating Token Index: 245

Text #5

Max Range: 7.8226. Min Range: -7.8226

Max Act: 7.3226. Min Act: -0.1700

Data Index: 1051035 (C4 (Web Text))

Max Activating Token Index: 182

Text #6

Max Range: 7.8226. Min Range: -7.8226

Max Act: 7.2913. Min Act: -0.1700

Data Index: 1269004 (C4 (Web Text))

Max Activating Token Index: 288

Text #7

Max Range: 7.8226. Min Range: -7.8226

Max Act: 7.2601. Min Act: -0.1700

Data Index: 381876 (C4 (Web Text))

Max Activating Token Index: 381

Text #8

Max Range: 7.8226. Min Range: -7.8226

Max Act: 7.1663. Min Act: -0.1700

Data Index: 32936 (C4 (Web Text))

Max Activating Token Index: 674

Text #9

Max Range: 7.8226. Min Range: -7.8226

Max Act: 7.2288. Min Act: -0.1700

Data Index: 71810 (C4 (Web Text))

Max Activating Token Index: 621

Text #10

Max Range: 7.8226. Min Range: -7.8226

Max Act: 7.1351. Min Act: -0.1700

Data Index: 533013 (C4 (Web Text))

Max Activating Token Index: 127

Text #11

Max Range: 7.8226. Min Range: -7.8226

Max Act: 7.1976. Min Act: -0.1700

Data Index: 802465 (C4 (Web Text))

Max Activating Token Index: 613

Text #12

Max Range: 7.8226. Min Range: -7.8226

Max Act: 7.1038. Min Act: -0.1700

Data Index: 594265 (C4 (Web Text))

Max Activating Token Index: 241

Text #13

Max Range: 7.8226. Min Range: -7.8226

Max Act: 7.1351. Min Act: -0.1700

Data Index: 630379 (C4 (Web Text))

Max Activating Token Index: 779

Text #14

Max Range: 7.8226. Min Range: -7.8226

Max Act: 7.1351. Min Act: -0.1700

Data Index: 878799 (C4 (Web Text))

Max Activating Token Index: 370

Text #15

Max Range: 7.8226. Min Range: -7.8226

Max Act: 7.1351. Min Act: -0.1700

Data Index: 418652 (C4 (Web Text))

Max Activating Token Index: 259

Text #16

Max Range: 7.8226. Min Range: -7.8226

Max Act: 7.0726. Min Act: -0.1700

Data Index: 1337989 (C4 (Web Text))

Max Activating Token Index: 313

Text #17

Max Range: 7.8226. Min Range: -7.8226

Max Act: 7.1038. Min Act: -0.1700

Data Index: 306834 (C4 (Web Text))

Max Activating Token Index: 691

Text #18

Max Range: 7.8226. Min Range: -7.8226

Max Act: 7.0726. Min Act: -0.1700

Data Index: 1141353 (C4 (Web Text))

Max Activating Token Index: 865

Text #19

Max Range: 7.8226. Min Range: -7.8226

Max Act: 7.1351. Min Act: -0.1700

Data Index: 703111 (C4 (Web Text))

Max Activating Token Index: 781