Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3939 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7630. Min Range: -0.7630

Max Act: 0.7028. Min Act: -0.0001

Data Index: 1113225 (C4 (Web Text))

Max Activating Token Index: 630

Text #1

Max Range: 0.7630. Min Range: -0.7630

Max Act: 0.7630. Min Act: -0.0001

Data Index: 619198 (C4 (Web Text))

Max Activating Token Index: 816

Text #2

Max Range: 0.7630. Min Range: -0.7630

Max Act: 0.6561. Min Act: -0.0002

Data Index: 189589 (C4 (Web Text))

Max Activating Token Index: 615

Text #3

Max Range: 0.7630. Min Range: -0.7630

Max Act: 0.7223. Min Act: -0.0001

Data Index: 1051895 (C4 (Web Text))

Max Activating Token Index: 959

Text #4

Max Range: 0.7630. Min Range: -0.7630

Max Act: 0.7054. Min Act: -0.0001

Data Index: 488632 (C4 (Web Text))

Max Activating Token Index: 937

Text #5

Max Range: 0.7630. Min Range: -0.7630

Max Act: 0.6918. Min Act: -0.0002

Data Index: 438666 (C4 (Web Text))

Max Activating Token Index: 798

Text #6

Max Range: 0.7630. Min Range: -0.7630

Max Act: 0.6783. Min Act: -0.0001

Data Index: 1061535 (C4 (Web Text))

Max Activating Token Index: 948

Text #7

Max Range: 0.7630. Min Range: -0.7630

Max Act: 0.6900. Min Act: -0.0001

Data Index: 869716 (C4 (Web Text))

Max Activating Token Index: 536

Text #8

Max Range: 0.7630. Min Range: -0.7630

Max Act: 0.6294. Min Act: -0.0002

Data Index: 93535 (C4 (Web Text))

Max Activating Token Index: 1012

Text #9

Max Range: 0.7630. Min Range: -0.7630

Max Act: 0.6863. Min Act: -0.0001

Data Index: 871940 (C4 (Web Text))

Max Activating Token Index: 308

Text #10

Max Range: 0.7630. Min Range: -0.7630

Max Act: 0.6761. Min Act: -0.0002

Data Index: 1241377 (C4 (Web Text))

Max Activating Token Index: 807

Text #11

Max Range: 0.7630. Min Range: -0.7630

Max Act: 0.6486. Min Act: -0.0002

Data Index: 412456 (C4 (Web Text))

Max Activating Token Index: 223

Text #12

Max Range: 0.7630. Min Range: -0.7630

Max Act: 0.6443. Min Act: -0.0001

Data Index: 910169 (C4 (Web Text))

Max Activating Token Index: 847

Text #13

Max Range: 0.7630. Min Range: -0.7630

Max Act: 0.6113. Min Act: -0.0002

Data Index: 1235588 (C4 (Web Text))

Max Activating Token Index: 351

Text #14

Max Range: 0.7630. Min Range: -0.7630

Max Act: 0.6369. Min Act: -0.0002

Data Index: 99906 (C4 (Web Text))

Max Activating Token Index: 191

Text #15

Max Range: 0.7630. Min Range: -0.7630

Max Act: 0.6201. Min Act: -0.0001

Data Index: 392713 (C4 (Web Text))

Max Activating Token Index: 391

Text #16

Max Range: 0.7630. Min Range: -0.7630

Max Act: 0.6336. Min Act: -0.0001

Data Index: 471760 (C4 (Web Text))

Max Activating Token Index: 926

Text #17

Max Range: 0.7630. Min Range: -0.7630

Max Act: 0.6766. Min Act: -0.0001

Data Index: 87715 (C4 (Web Text))

Max Activating Token Index: 571

Text #18

Max Range: 0.7630. Min Range: -0.7630

Max Act: 0.6878. Min Act: -0.0001

Data Index: 1122598 (C4 (Web Text))

Max Activating Token Index: 669

Text #19

Max Range: 0.7630. Min Range: -0.7630

Max Act: 0.6701. Min Act: -0.0001

Data Index: 1328189 (C4 (Web Text))

Max Activating Token Index: 222