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

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

Neuron 2882 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2805. Min Range: -1.2805

Max Act: 1.2805. Min Act: -0.0001

Data Index: 989207 (C4 (Web Text))

Max Activating Token Index: 397

Text #1

Max Range: 1.2805. Min Range: -1.2805

Max Act: 1.1716. Min Act: -0.0001

Data Index: 637906 (C4 (Web Text))

Max Activating Token Index: 511

Text #2

Max Range: 1.2805. Min Range: -1.2805

Max Act: 1.1223. Min Act: -0.0001

Data Index: 438112 (C4 (Web Text))

Max Activating Token Index: 12

Text #3

Max Range: 1.2805. Min Range: -1.2805

Max Act: 1.1541. Min Act: -0.0001

Data Index: 1312485 (C4 (Web Text))

Max Activating Token Index: 1013

Text #4

Max Range: 1.2805. Min Range: -1.2805

Max Act: 1.1235. Min Act: -0.0001

Data Index: 245694 (C4 (Web Text))

Max Activating Token Index: 845

Text #5

Max Range: 1.2805. Min Range: -1.2805

Max Act: 1.1161. Min Act: -0.0001

Data Index: 34395 (C4 (Web Text))

Max Activating Token Index: 991

Text #6

Max Range: 1.2805. Min Range: -1.2805

Max Act: 1.0914. Min Act: -0.0001

Data Index: 86212 (C4 (Web Text))

Max Activating Token Index: 201

Text #7

Max Range: 1.2805. Min Range: -1.2805

Max Act: 0.9645. Min Act: -0.0001

Data Index: 270783 (C4 (Web Text))

Max Activating Token Index: 346

Text #8

Max Range: 1.2805. Min Range: -1.2805

Max Act: 1.0235. Min Act: -0.0001

Data Index: 20484 (C4 (Web Text))

Max Activating Token Index: 211

Text #9

Max Range: 1.2805. Min Range: -1.2805

Max Act: 0.9290. Min Act: -0.0001

Data Index: 634199 (C4 (Web Text))

Max Activating Token Index: 223

Text #10

Max Range: 1.2805. Min Range: -1.2805

Max Act: 0.9878. Min Act: -0.0001

Data Index: 385515 (C4 (Web Text))

Max Activating Token Index: 716

Text #11

Max Range: 1.2805. Min Range: -1.2805

Max Act: 0.7972. Min Act: -0.0001

Data Index: 816221 (C4 (Web Text))

Max Activating Token Index: 418

Text #12

Max Range: 1.2805. Min Range: -1.2805

Max Act: 0.9301. Min Act: -0.0001

Data Index: 1061575 (C4 (Web Text))

Max Activating Token Index: 106

Text #13

Max Range: 1.2805. Min Range: -1.2805

Max Act: 0.7168. Min Act: -0.0001

Data Index: 327658 (C4 (Web Text))

Max Activating Token Index: 306

Text #14

Max Range: 1.2805. Min Range: -1.2805

Max Act: 0.8414. Min Act: -0.0001

Data Index: 100399 (C4 (Web Text))

Max Activating Token Index: 429

Text #15

Max Range: 1.2805. Min Range: -1.2805

Max Act: 0.8037. Min Act: -0.0001

Data Index: 18772 (C4 (Web Text))

Max Activating Token Index: 130

Text #16

Max Range: 1.2805. Min Range: -1.2805

Max Act: 0.8650. Min Act: -0.0001

Data Index: 904886 (C4 (Web Text))

Max Activating Token Index: 12

Text #17

Max Range: 1.2805. Min Range: -1.2805

Max Act: 0.8124. Min Act: -0.0001

Data Index: 541292 (C4 (Web Text))

Max Activating Token Index: 695

Text #18

Max Range: 1.2805. Min Range: -1.2805

Max Act: 0.8897. Min Act: -0.0001

Data Index: 156009 (C4 (Web Text))

Max Activating Token Index: 215

Text #19

Max Range: 1.2805. Min Range: -1.2805

Max Act: 0.8321. Min Act: -0.0001

Data Index: 945105 (C4 (Web Text))

Max Activating Token Index: 194