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

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

Neuron 1557 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1354. Min Range: -0.1354

Max Act: 0.1326. Min Act: -0.0001

Data Index: 28441 (C4 (Web Text))

Max Activating Token Index: 644

Text #1

Max Range: 0.1354. Min Range: -0.1354

Max Act: 0.1300. Min Act: -0.0000

Data Index: 1188286 (C4 (Web Text))

Max Activating Token Index: 254

Text #2

Max Range: 0.1354. Min Range: -0.1354

Max Act: 0.1310. Min Act: -0.0000

Data Index: 44055 (C4 (Web Text))

Max Activating Token Index: 930

Text #3

Max Range: 0.1354. Min Range: -0.1354

Max Act: 0.1354. Min Act: -0.0001

Data Index: 11914 (C4 (Web Text))

Max Activating Token Index: 476

Text #4

Max Range: 0.1354. Min Range: -0.1354

Max Act: 0.1310. Min Act: -0.0000

Data Index: 408577 (C4 (Web Text))

Max Activating Token Index: 246

Text #5

Max Range: 0.1354. Min Range: -0.1354

Max Act: 0.1221. Min Act: -0.0000

Data Index: 807919 (C4 (Web Text))

Max Activating Token Index: 996

Text #6

Max Range: 0.1354. Min Range: -0.1354

Max Act: 0.1189. Min Act: -0.0000

Data Index: 228619 (C4 (Web Text))

Max Activating Token Index: 588

Text #7

Max Range: 0.1354. Min Range: -0.1354

Max Act: 0.1147. Min Act: -0.0000

Data Index: 47617 (C4 (Web Text))

Max Activating Token Index: 119

Text #8

Max Range: 0.1354. Min Range: -0.1354

Max Act: 0.1134. Min Act: -0.0000

Data Index: 1119841 (C4 (Web Text))

Max Activating Token Index: 70

Text #9

Max Range: 0.1354. Min Range: -0.1354

Max Act: 0.1121. Min Act: -0.0000

Data Index: 43936 (C4 (Web Text))

Max Activating Token Index: 412

Text #10

Max Range: 0.1354. Min Range: -0.1354

Max Act: 0.1117. Min Act: -0.0000

Data Index: 929974 (C4 (Web Text))

Max Activating Token Index: 69

Text #11

Max Range: 0.1354. Min Range: -0.1354

Max Act: 0.1112. Min Act: -0.0000

Data Index: 1197987 (C4 (Web Text))

Max Activating Token Index: 659

Text #12

Max Range: 0.1354. Min Range: -0.1354

Max Act: 0.1154. Min Act: -0.0000

Data Index: 44957 (C4 (Web Text))

Max Activating Token Index: 142

Text #13

Max Range: 0.1354. Min Range: -0.1354

Max Act: 0.1025. Min Act: -0.0000

Data Index: 1007187 (C4 (Web Text))

Max Activating Token Index: 967

Text #14

Max Range: 0.1354. Min Range: -0.1354

Max Act: 0.1052. Min Act: -0.0000

Data Index: 852630 (C4 (Web Text))

Max Activating Token Index: 672

Text #15

Max Range: 0.1354. Min Range: -0.1354

Max Act: 0.1014. Min Act: -0.0000

Data Index: 166762 (C4 (Web Text))

Max Activating Token Index: 63

Text #16

Max Range: 0.1354. Min Range: -0.1354

Max Act: 0.1114. Min Act: -0.0001

Data Index: 483799 (C4 (Web Text))

Max Activating Token Index: 745

Text #17

Max Range: 0.1354. Min Range: -0.1354

Max Act: 0.0986. Min Act: -0.0001

Data Index: 714208 (C4 (Web Text))

Max Activating Token Index: 373

Text #18

Max Range: 0.1354. Min Range: -0.1354

Max Act: 0.1057. Min Act: -0.0000

Data Index: 936114 (C4 (Web Text))

Max Activating Token Index: 10

Text #19

Max Range: 0.1354. Min Range: -0.1354

Max Act: 0.0942. Min Act: -0.0001

Data Index: 198536 (C4 (Web Text))

Max Activating Token Index: 441