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

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

Neuron 20 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5316. Min Range: -5.5316

Max Act: 5.5316. Min Act: -0.1700

Data Index: 1006530 (C4 (Web Text))

Max Activating Token Index: 647

Text #1

Max Range: 5.5316. Min Range: -5.5316

Max Act: 5.5004. Min Act: -0.1700

Data Index: 1144168 (C4 (Web Text))

Max Activating Token Index: 279

Text #2

Max Range: 5.5316. Min Range: -5.5316

Max Act: 5.4066. Min Act: -0.1700

Data Index: 784824 (C4 (Web Text))

Max Activating Token Index: 633

Text #3

Max Range: 5.5316. Min Range: -5.5316

Max Act: 5.3754. Min Act: -0.1700

Data Index: 485783 (C4 (Web Text))

Max Activating Token Index: 316

Text #4

Max Range: 5.5316. Min Range: -5.5316

Max Act: 5.3441. Min Act: -0.1700

Data Index: 261522 (C4 (Web Text))

Max Activating Token Index: 317

Text #5

Max Range: 5.5316. Min Range: -5.5316

Max Act: 5.3129. Min Act: -0.1699

Data Index: 910100 (C4 (Web Text))

Max Activating Token Index: 956

Text #6

Max Range: 5.5316. Min Range: -5.5316

Max Act: 5.3129. Min Act: -0.1700

Data Index: 410662 (C4 (Web Text))

Max Activating Token Index: 158

Text #7

Max Range: 5.5316. Min Range: -5.5316

Max Act: 5.3129. Min Act: -0.1700

Data Index: 819405 (C4 (Web Text))

Max Activating Token Index: 173

Text #8

Max Range: 5.5316. Min Range: -5.5316

Max Act: 5.3129. Min Act: -0.1700

Data Index: 1086844 (C4 (Web Text))

Max Activating Token Index: 477

Text #9

Max Range: 5.5316. Min Range: -5.5316

Max Act: 5.3129. Min Act: -0.1700

Data Index: 587349 (C4 (Web Text))

Max Activating Token Index: 239

Text #10

Max Range: 5.5316. Min Range: -5.5316

Max Act: 5.2504. Min Act: -0.1700

Data Index: 174821 (C4 (Web Text))

Max Activating Token Index: 460

Text #11

Max Range: 5.5316. Min Range: -5.5316

Max Act: 5.2504. Min Act: -0.1700

Data Index: 113509 (C4 (Web Text))

Max Activating Token Index: 921

Text #12

Max Range: 5.5316. Min Range: -5.5316

Max Act: 5.2504. Min Act: -0.1699

Data Index: 943916 (C4 (Web Text))

Max Activating Token Index: 758

Text #13

Max Range: 5.5316. Min Range: -5.5316

Max Act: 5.2504. Min Act: -0.1700

Data Index: 1020860 (C4 (Web Text))

Max Activating Token Index: 914

Text #14

Max Range: 5.5316. Min Range: -5.5316

Max Act: 5.2816. Min Act: -0.1700

Data Index: 509696 (C4 (Web Text))

Max Activating Token Index: 814

Text #15

Max Range: 5.5316. Min Range: -5.5316

Max Act: 5.2504. Min Act: -0.1700

Data Index: 1072634 (C4 (Web Text))

Max Activating Token Index: 571

Text #16

Max Range: 5.5316. Min Range: -5.5316

Max Act: 5.2504. Min Act: -0.1700

Data Index: 281308 (C4 (Web Text))

Max Activating Token Index: 424

Text #17

Max Range: 5.5316. Min Range: -5.5316

Max Act: 5.2504. Min Act: -0.1700

Data Index: 106916 (C4 (Web Text))

Max Activating Token Index: 288

Text #18

Max Range: 5.5316. Min Range: -5.5316

Max Act: 5.2191. Min Act: -0.1700

Data Index: 183405 (C4 (Web Text))

Max Activating Token Index: 575

Text #19

Max Range: 5.5316. Min Range: -5.5316

Max Act: 5.2191. Min Act: -0.1700

Data Index: 941974 (C4 (Web Text))

Max Activating Token Index: 878