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

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

Neuron 760 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: 3.6567. Min Range: -3.6567

Max Act: 3.6254. Min Act: -0.1700

Data Index: 349292 (C4 (Web Text))

Max Activating Token Index: 513

Text #1

Max Range: 3.6567. Min Range: -3.6567

Max Act: 3.6567. Min Act: -0.1700

Data Index: 80924 (C4 (Web Text))

Max Activating Token Index: 992

Text #2

Max Range: 3.6567. Min Range: -3.6567

Max Act: 3.6254. Min Act: -0.1700

Data Index: 1129434 (C4 (Web Text))

Max Activating Token Index: 204

Text #3

Max Range: 3.6567. Min Range: -3.6567

Max Act: 3.5628. Min Act: -0.1700

Data Index: 1284996 (C4 (Web Text))

Max Activating Token Index: 421

Text #4

Max Range: 3.6567. Min Range: -3.6567

Max Act: 3.5628. Min Act: -0.1700

Data Index: 818844 (C4 (Web Text))

Max Activating Token Index: 952

Text #5

Max Range: 3.6567. Min Range: -3.6567

Max Act: 3.5628. Min Act: -0.1700

Data Index: 744726 (C4 (Web Text))

Max Activating Token Index: 175

Text #6

Max Range: 3.6567. Min Range: -3.6567

Max Act: 3.5471. Min Act: -0.1700

Data Index: 200482 (C4 (Web Text))

Max Activating Token Index: 412

Text #7

Max Range: 3.6567. Min Range: -3.6567

Max Act: 3.5471. Min Act: -0.1700

Data Index: 1093306 (C4 (Web Text))

Max Activating Token Index: 284

Text #8

Max Range: 3.6567. Min Range: -3.6567

Max Act: 3.5471. Min Act: -0.1700

Data Index: 640978 (C4 (Web Text))

Max Activating Token Index: 268

Text #9

Max Range: 3.6567. Min Range: -3.6567

Max Act: 3.5315. Min Act: -0.1700

Data Index: 235363 (C4 (Web Text))

Max Activating Token Index: 481

Text #10

Max Range: 3.6567. Min Range: -3.6567

Max Act: 3.5628. Min Act: -0.1700

Data Index: 829234 (C4 (Web Text))

Max Activating Token Index: 668

Text #11

Max Range: 3.6567. Min Range: -3.6567

Max Act: 3.5471. Min Act: -0.1700

Data Index: 979794 (C4 (Web Text))

Max Activating Token Index: 678

Text #12

Max Range: 3.6567. Min Range: -3.6567

Max Act: 3.5471. Min Act: -0.1700

Data Index: 1340949 (C4 (Web Text))

Max Activating Token Index: 314

Text #13

Max Range: 3.6567. Min Range: -3.6567

Max Act: 3.5158. Min Act: -0.1700

Data Index: 24411 (C4 (Web Text))

Max Activating Token Index: 416

Text #14

Max Range: 3.6567. Min Range: -3.6567

Max Act: 3.5471. Min Act: -0.1700

Data Index: 1332433 (C4 (Web Text))

Max Activating Token Index: 180

Text #15

Max Range: 3.6567. Min Range: -3.6567

Max Act: 3.5628. Min Act: -0.1700

Data Index: 142651 (C4 (Web Text))

Max Activating Token Index: 377

Text #16

Max Range: 3.6567. Min Range: -3.6567

Max Act: 3.5315. Min Act: -0.1700

Data Index: 264093 (C4 (Web Text))

Max Activating Token Index: 157

Text #17

Max Range: 3.6567. Min Range: -3.6567

Max Act: 3.5315. Min Act: -0.1700

Data Index: 374365 (C4 (Web Text))

Max Activating Token Index: 122

Text #18

Max Range: 3.6567. Min Range: -3.6567

Max Act: 3.5001. Min Act: -0.1700

Data Index: 588265 (C4 (Web Text))

Max Activating Token Index: 421

Text #19

Max Range: 3.6567. Min Range: -3.6567

Max Act: 3.5315. Min Act: -0.1700

Data Index: 1083679 (C4 (Web Text))

Max Activating Token Index: 405