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

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

Neuron 4338 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.9563. Min Act: -0.0000

Data Index: 1143931 (C4 (Web Text))

Max Activating Token Index: 934

Text #1

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.8972. Min Act: -0.0000

Data Index: 685864 (C4 (Web Text))

Max Activating Token Index: 1005

Text #2

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.8639. Min Act: -0.0000

Data Index: 305563 (C4 (Web Text))

Max Activating Token Index: 339

Text #3

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.8610. Min Act: -0.0000

Data Index: 1341971 (C4 (Web Text))

Max Activating Token Index: 268

Text #4

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.8619. Min Act: -0.0000

Data Index: 367091 (C4 (Web Text))

Max Activating Token Index: 388

Text #5

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.7915. Min Act: -0.0000

Data Index: 511139 (C4 (Web Text))

Max Activating Token Index: 442

Text #6

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.7820. Min Act: -0.0000

Data Index: 479193 (C4 (Web Text))

Max Activating Token Index: 309

Text #7

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.8054. Min Act: -0.0000

Data Index: 1127439 (C4 (Web Text))

Max Activating Token Index: 163

Text #8

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.7652. Min Act: -0.0000

Data Index: 819711 (C4 (Web Text))

Max Activating Token Index: 361

Text #9

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.6807. Min Act: -0.0000

Data Index: 1075179 (C4 (Web Text))

Max Activating Token Index: 606

Text #10

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.7198. Min Act: -0.0000

Data Index: 383176 (C4 (Web Text))

Max Activating Token Index: 404

Text #11

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.7159. Min Act: -0.0000

Data Index: 1194287 (C4 (Web Text))

Max Activating Token Index: 561

Text #12

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.7267. Min Act: -0.0000

Data Index: 1357916 (C4 (Web Text))

Max Activating Token Index: 590

Text #13

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.7000. Min Act: -0.0000

Data Index: 764073 (C4 (Web Text))

Max Activating Token Index: 727

Text #14

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.7306. Min Act: -0.0000

Data Index: 733555 (C4 (Web Text))

Max Activating Token Index: 761

Text #15

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.7176. Min Act: -0.0000

Data Index: 1068970 (C4 (Web Text))

Max Activating Token Index: 84

Text #16

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.6764. Min Act: -0.0000

Data Index: 577126 (C4 (Web Text))

Max Activating Token Index: 76

Text #17

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.7341. Min Act: -0.0000

Data Index: 1149870 (C4 (Web Text))

Max Activating Token Index: 950

Text #18

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.6873. Min Act: -0.0000

Data Index: 1016769 (C4 (Web Text))

Max Activating Token Index: 816

Text #19

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.6830. Min Act: -0.0000

Data Index: 987806 (C4 (Web Text))

Max Activating Token Index: 516