Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5420 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 7.8459. Min Range: -7.8459

Max Act: 7.8459. Min Act: -0.0000

Data Index: 40706 (C4 (Web Text))

Max Activating Token Index: 767

Text #1

Max Range: 7.8459. Min Range: -7.8459

Max Act: 7.2671. Min Act: -0.0000

Data Index: 309965 (C4 (Web Text))

Max Activating Token Index: 984

Text #2

Max Range: 7.8459. Min Range: -7.8459

Max Act: 6.7285. Min Act: -0.0000

Data Index: 1007019 (C4 (Web Text))

Max Activating Token Index: 279

Text #3

Max Range: 7.8459. Min Range: -7.8459

Max Act: 6.6999. Min Act: -0.0000

Data Index: 912927 (C4 (Web Text))

Max Activating Token Index: 567

Text #4

Max Range: 7.8459. Min Range: -7.8459

Max Act: 6.5019. Min Act: -0.0000

Data Index: 160505 (C4 (Web Text))

Max Activating Token Index: 380

Text #5

Max Range: 7.8459. Min Range: -7.8459

Max Act: 6.5725. Min Act: -0.0000

Data Index: 1075007 (C4 (Web Text))

Max Activating Token Index: 903

Text #6

Max Range: 7.8459. Min Range: -7.8459

Max Act: 6.3352. Min Act: -0.0000

Data Index: 439480 (C4 (Web Text))

Max Activating Token Index: 544

Text #7

Max Range: 7.8459. Min Range: -7.8459

Max Act: 6.1569. Min Act: -0.0000

Data Index: 1162337 (C4 (Web Text))

Max Activating Token Index: 810

Text #8

Max Range: 7.8459. Min Range: -7.8459

Max Act: 6.5192. Min Act: -0.0000

Data Index: 1217231 (C4 (Web Text))

Max Activating Token Index: 511

Text #9

Max Range: 7.8459. Min Range: -7.8459

Max Act: 6.5043. Min Act: -0.0000

Data Index: 908649 (C4 (Web Text))

Max Activating Token Index: 499

Text #10

Max Range: 7.8459. Min Range: -7.8459

Max Act: 6.3250. Min Act: -0.0000

Data Index: 1185105 (C4 (Web Text))

Max Activating Token Index: 244

Text #11

Max Range: 7.8459. Min Range: -7.8459

Max Act: 6.5097. Min Act: -0.0000

Data Index: 494564 (C4 (Web Text))

Max Activating Token Index: 939

Text #12

Max Range: 7.8459. Min Range: -7.8459

Max Act: 5.9204. Min Act: -0.0000

Data Index: 574994 (C4 (Web Text))

Max Activating Token Index: 426

Text #13

Max Range: 7.8459. Min Range: -7.8459

Max Act: 6.5878. Min Act: -0.0000

Data Index: 224274 (C4 (Web Text))

Max Activating Token Index: 173

Text #14

Max Range: 7.8459. Min Range: -7.8459

Max Act: 5.9824. Min Act: -0.0000

Data Index: 716110 (C4 (Web Text))

Max Activating Token Index: 399

Text #15

Max Range: 7.8459. Min Range: -7.8459

Max Act: 5.9370. Min Act: -0.0000

Data Index: 1309740 (C4 (Web Text))

Max Activating Token Index: 792

Text #16

Max Range: 7.8459. Min Range: -7.8459

Max Act: 5.6977. Min Act: -0.0000

Data Index: 835728 (C4 (Web Text))

Max Activating Token Index: 721

Text #17

Max Range: 7.8459. Min Range: -7.8459

Max Act: 5.8510. Min Act: -0.0000

Data Index: 214101 (C4 (Web Text))

Max Activating Token Index: 485

Text #18

Max Range: 7.8459. Min Range: -7.8459

Max Act: 5.8541. Min Act: -0.0000

Data Index: 907460 (C4 (Web Text))

Max Activating Token Index: 398

Text #19

Max Range: 7.8459. Min Range: -7.8459

Max Act: 5.4329. Min Act: -0.0000

Data Index: 310319 (C4 (Web Text))

Max Activating Token Index: 97