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

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

Neuron 801 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: 6.0527. Min Range: -6.0527

Max Act: 6.0527. Min Act: -0.1700

Data Index: 920394 (C4 (Web Text))

Max Activating Token Index: 77

Text #1

Max Range: 6.0527. Min Range: -6.0527

Max Act: 5.6777. Min Act: -0.1700

Data Index: 947226 (C4 (Web Text))

Max Activating Token Index: 943

Text #2

Max Range: 6.0527. Min Range: -6.0527

Max Act: 5.6777. Min Act: -0.1700

Data Index: 1279353 (C4 (Web Text))

Max Activating Token Index: 900

Text #3

Max Range: 6.0527. Min Range: -6.0527

Max Act: 5.6152. Min Act: -0.1700

Data Index: 949284 (C4 (Web Text))

Max Activating Token Index: 775

Text #4

Max Range: 6.0527. Min Range: -6.0527

Max Act: 5.5214. Min Act: -0.1700

Data Index: 682186 (C4 (Web Text))

Max Activating Token Index: 272

Text #5

Max Range: 6.0527. Min Range: -6.0527

Max Act: 5.4277. Min Act: -0.1700

Data Index: 569267 (C4 (Web Text))

Max Activating Token Index: 877

Text #6

Max Range: 6.0527. Min Range: -6.0527

Max Act: 5.4589. Min Act: -0.1700

Data Index: 1081739 (C4 (Web Text))

Max Activating Token Index: 643

Text #7

Max Range: 6.0527. Min Range: -6.0527

Max Act: 5.4277. Min Act: -0.1700

Data Index: 796817 (C4 (Web Text))

Max Activating Token Index: 493

Text #8

Max Range: 6.0527. Min Range: -6.0527

Max Act: 5.4277. Min Act: -0.1700

Data Index: 458902 (C4 (Web Text))

Max Activating Token Index: 786

Text #9

Max Range: 6.0527. Min Range: -6.0527

Max Act: 5.3339. Min Act: -0.1700

Data Index: 1262477 (C4 (Web Text))

Max Activating Token Index: 700

Text #10

Max Range: 6.0527. Min Range: -6.0527

Max Act: 5.3964. Min Act: -0.1700

Data Index: 47068 (C4 (Web Text))

Max Activating Token Index: 226

Text #11

Max Range: 6.0527. Min Range: -6.0527

Max Act: 5.3652. Min Act: -0.1700

Data Index: 25218 (C4 (Web Text))

Max Activating Token Index: 436

Text #12

Max Range: 6.0527. Min Range: -6.0527

Max Act: 5.3652. Min Act: -0.1700

Data Index: 1247758 (C4 (Web Text))

Max Activating Token Index: 353

Text #13

Max Range: 6.0527. Min Range: -6.0527

Max Act: 5.3652. Min Act: -0.1700

Data Index: 93942 (C4 (Web Text))

Max Activating Token Index: 867

Text #14

Max Range: 6.0527. Min Range: -6.0527

Max Act: 5.3964. Min Act: -0.1700

Data Index: 1328869 (C4 (Web Text))

Max Activating Token Index: 774

Text #15

Max Range: 6.0527. Min Range: -6.0527

Max Act: 5.3652. Min Act: -0.1700

Data Index: 948832 (C4 (Web Text))

Max Activating Token Index: 583

Text #16

Max Range: 6.0527. Min Range: -6.0527

Max Act: 5.3339. Min Act: -0.1700

Data Index: 1033088 (C4 (Web Text))

Max Activating Token Index: 991

Text #17

Max Range: 6.0527. Min Range: -6.0527

Max Act: 5.3652. Min Act: -0.1700

Data Index: 18639 (C4 (Web Text))

Max Activating Token Index: 133

Text #18

Max Range: 6.0527. Min Range: -6.0527

Max Act: 5.3339. Min Act: -0.1700

Data Index: 15623 (C4 (Web Text))

Max Activating Token Index: 289

Text #19

Max Range: 6.0527. Min Range: -6.0527

Max Act: 5.3339. Min Act: -0.1700

Data Index: 57162 (C4 (Web Text))

Max Activating Token Index: 241