Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1062 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.1270. Min Range: -1.1270

Max Act: 1.1270. Min Act: -0.0001

Data Index: 175043 (C4 (Web Text))

Max Activating Token Index: 625

Text #1

Max Range: 1.1270. Min Range: -1.1270

Max Act: 0.7295. Min Act: -0.0001

Data Index: 257533 (C4 (Web Text))

Max Activating Token Index: 854

Text #2

Max Range: 1.1270. Min Range: -1.1270

Max Act: 0.6654. Min Act: -0.0001

Data Index: 240810 (C4 (Web Text))

Max Activating Token Index: 849

Text #3

Max Range: 1.1270. Min Range: -1.1270

Max Act: 0.7230. Min Act: -0.0001

Data Index: 771866 (C4 (Web Text))

Max Activating Token Index: 301

Text #4

Max Range: 1.1270. Min Range: -1.1270

Max Act: 0.7411. Min Act: -0.0001

Data Index: 331337 (C4 (Web Text))

Max Activating Token Index: 754

Text #5

Max Range: 1.1270. Min Range: -1.1270

Max Act: 0.6716. Min Act: -0.0001

Data Index: 900110 (C4 (Web Text))

Max Activating Token Index: 357

Text #6

Max Range: 1.1270. Min Range: -1.1270

Max Act: 0.6448. Min Act: -0.0001

Data Index: 565749 (C4 (Web Text))

Max Activating Token Index: 806

Text #7

Max Range: 1.1270. Min Range: -1.1270

Max Act: 0.7121. Min Act: -0.0001

Data Index: 438405 (C4 (Web Text))

Max Activating Token Index: 676

Text #8

Max Range: 1.1270. Min Range: -1.1270

Max Act: 0.6937. Min Act: -0.0001

Data Index: 152867 (C4 (Web Text))

Max Activating Token Index: 798

Text #9

Max Range: 1.1270. Min Range: -1.1270

Max Act: 0.6584. Min Act: -0.0001

Data Index: 1058226 (C4 (Web Text))

Max Activating Token Index: 97

Text #10

Max Range: 1.1270. Min Range: -1.1270

Max Act: 0.5802. Min Act: -0.0001

Data Index: 46302 (C4 (Web Text))

Max Activating Token Index: 994

Text #11

Max Range: 1.1270. Min Range: -1.1270

Max Act: 0.5962. Min Act: -0.0001

Data Index: 1348878 (C4 (Web Text))

Max Activating Token Index: 926

Text #12

Max Range: 1.1270. Min Range: -1.1270

Max Act: 0.6660. Min Act: -0.0001

Data Index: 160548 (C4 (Web Text))

Max Activating Token Index: 10

Text #13

Max Range: 1.1270. Min Range: -1.1270

Max Act: 0.6050. Min Act: -0.0001

Data Index: 1317729 (C4 (Web Text))

Max Activating Token Index: 286

Text #14

Max Range: 1.1270. Min Range: -1.1270

Max Act: 0.6632. Min Act: -0.0001

Data Index: 731861 (C4 (Web Text))

Max Activating Token Index: 859

Text #15

Max Range: 1.1270. Min Range: -1.1270

Max Act: 0.6363. Min Act: -0.0001

Data Index: 472989 (C4 (Web Text))

Max Activating Token Index: 995

Text #16

Max Range: 1.1270. Min Range: -1.1270

Max Act: 0.6883. Min Act: -0.0001

Data Index: 1016392 (C4 (Web Text))

Max Activating Token Index: 896

Text #17

Max Range: 1.1270. Min Range: -1.1270

Max Act: 0.6323. Min Act: -0.0001

Data Index: 907815 (C4 (Web Text))

Max Activating Token Index: 1002

Text #18

Max Range: 1.1270. Min Range: -1.1270

Max Act: 0.5666. Min Act: -0.0001

Data Index: 1241854 (C4 (Web Text))

Max Activating Token Index: 213

Text #19

Max Range: 1.1270. Min Range: -1.1270

Max Act: 0.5460. Min Act: -0.0001

Data Index: 262194 (C4 (Web Text))

Max Activating Token Index: 769