Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 441 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 4.4165. Min Range: -4.4165

Max Act: 4.4165. Min Act: -0.1700

Data Index: 386456 (C4 (Web Text))

Max Activating Token Index: 674

Text #1

Max Range: 4.4165. Min Range: -4.4165

Max Act: 4.4165. Min Act: -0.1700

Data Index: 456724 (C4 (Web Text))

Max Activating Token Index: 471

Text #2

Max Range: 4.4165. Min Range: -4.4165

Max Act: 4.2915. Min Act: -0.1698

Data Index: 608250 (C4 (Web Text))

Max Activating Token Index: 327

Text #3

Max Range: 4.4165. Min Range: -4.4165

Max Act: 4.2602. Min Act: -0.1700

Data Index: 1312413 (C4 (Web Text))

Max Activating Token Index: 678

Text #4

Max Range: 4.4165. Min Range: -4.4165

Max Act: 4.2915. Min Act: -0.1699

Data Index: 552090 (C4 (Web Text))

Max Activating Token Index: 438

Text #5

Max Range: 4.4165. Min Range: -4.4165

Max Act: 4.1977. Min Act: -0.1699

Data Index: 1203637 (C4 (Web Text))

Max Activating Token Index: 118

Text #6

Max Range: 4.4165. Min Range: -4.4165

Max Act: 4.2290. Min Act: -0.1699

Data Index: 836480 (C4 (Web Text))

Max Activating Token Index: 516

Text #7

Max Range: 4.4165. Min Range: -4.4165

Max Act: 4.2915. Min Act: -0.1699

Data Index: 646851 (C4 (Web Text))

Max Activating Token Index: 926

Text #8

Max Range: 4.4165. Min Range: -4.4165

Max Act: 4.2290. Min Act: -0.1700

Data Index: 1067764 (C4 (Web Text))

Max Activating Token Index: 395

Text #9

Max Range: 4.4165. Min Range: -4.4165

Max Act: 4.1977. Min Act: -0.1700

Data Index: 167852 (C4 (Web Text))

Max Activating Token Index: 566

Text #10

Max Range: 4.4165. Min Range: -4.4165

Max Act: 4.1664. Min Act: -0.1639

Data Index: 701113 (C4 (Web Text))

Max Activating Token Index: 222

Text #11

Max Range: 4.4165. Min Range: -4.4165

Max Act: 4.1977. Min Act: -0.1700

Data Index: 319367 (C4 (Web Text))

Max Activating Token Index: 257

Text #12

Max Range: 4.4165. Min Range: -4.4165

Max Act: 4.1664. Min Act: -0.1700

Data Index: 234598 (C4 (Web Text))

Max Activating Token Index: 156

Text #13

Max Range: 4.4165. Min Range: -4.4165

Max Act: 4.1039. Min Act: -0.1700

Data Index: 141707 (C4 (Web Text))

Max Activating Token Index: 99

Text #14

Max Range: 4.4165. Min Range: -4.4165

Max Act: 4.1664. Min Act: -0.1700

Data Index: 1249681 (C4 (Web Text))

Max Activating Token Index: 552

Text #15

Max Range: 4.4165. Min Range: -4.4165

Max Act: 4.1039. Min Act: -0.1699

Data Index: 1057260 (C4 (Web Text))

Max Activating Token Index: 130

Text #16

Max Range: 4.4165. Min Range: -4.4165

Max Act: 4.1039. Min Act: -0.1700

Data Index: 915716 (C4 (Web Text))

Max Activating Token Index: 626

Text #17

Max Range: 4.4165. Min Range: -4.4165

Max Act: 4.1039. Min Act: -0.1700

Data Index: 889924 (C4 (Web Text))

Max Activating Token Index: 260

Text #18

Max Range: 4.4165. Min Range: -4.4165

Max Act: 4.1039. Min Act: -0.1700

Data Index: 631504 (C4 (Web Text))

Max Activating Token Index: 811

Text #19

Max Range: 4.4165. Min Range: -4.4165

Max Act: 4.0727. Min Act: -0.1700

Data Index: 467006 (C4 (Web Text))

Max Activating Token Index: 315