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

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

Neuron 4875 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: 0.2992. Min Range: -0.2992

Max Act: 0.2992. Min Act: -0.0001

Data Index: 145605 (C4 (Web Text))

Max Activating Token Index: 123

Text #1

Max Range: 0.2992. Min Range: -0.2992

Max Act: 0.2805. Min Act: -0.0001

Data Index: 854339 (C4 (Web Text))

Max Activating Token Index: 150

Text #2

Max Range: 0.2992. Min Range: -0.2992

Max Act: 0.2453. Min Act: -0.0001

Data Index: 68283 (C4 (Web Text))

Max Activating Token Index: 77

Text #3

Max Range: 0.2992. Min Range: -0.2992

Max Act: 0.2527. Min Act: -0.0001

Data Index: 244185 (C4 (Web Text))

Max Activating Token Index: 566

Text #4

Max Range: 0.2992. Min Range: -0.2992

Max Act: 0.2386. Min Act: -0.0001

Data Index: 720982 (C4 (Web Text))

Max Activating Token Index: 422

Text #5

Max Range: 0.2992. Min Range: -0.2992

Max Act: 0.2346. Min Act: -0.0001

Data Index: 1264848 (C4 (Web Text))

Max Activating Token Index: 31

Text #6

Max Range: 0.2992. Min Range: -0.2992

Max Act: 0.2327. Min Act: -0.0001

Data Index: 1159895 (C4 (Web Text))

Max Activating Token Index: 27

Text #7

Max Range: 0.2992. Min Range: -0.2992

Max Act: 0.2223. Min Act: -0.0001

Data Index: 975504 (C4 (Web Text))

Max Activating Token Index: 177

Text #8

Max Range: 0.2992. Min Range: -0.2992

Max Act: 0.2430. Min Act: -0.0001

Data Index: 1344569 (C4 (Web Text))

Max Activating Token Index: 425

Text #9

Max Range: 0.2992. Min Range: -0.2992

Max Act: 0.2441. Min Act: -0.0001

Data Index: 738421 (C4 (Web Text))

Max Activating Token Index: 672

Text #10

Max Range: 0.2992. Min Range: -0.2992

Max Act: 0.2353. Min Act: -0.0001

Data Index: 532461 (C4 (Web Text))

Max Activating Token Index: 164

Text #11

Max Range: 0.2992. Min Range: -0.2992

Max Act: 0.2259. Min Act: -0.0001

Data Index: 740341 (C4 (Web Text))

Max Activating Token Index: 136

Text #12

Max Range: 0.2992. Min Range: -0.2992

Max Act: 0.2258. Min Act: -0.0001

Data Index: 331053 (C4 (Web Text))

Max Activating Token Index: 61

Text #13

Max Range: 0.2992. Min Range: -0.2992

Max Act: 0.2242. Min Act: -0.0001

Data Index: 1122384 (C4 (Web Text))

Max Activating Token Index: 152

Text #14

Max Range: 0.2992. Min Range: -0.2992

Max Act: 0.2310. Min Act: -0.0001

Data Index: 1339579 (C4 (Web Text))

Max Activating Token Index: 14

Text #15

Max Range: 0.2992. Min Range: -0.2992

Max Act: 0.2235. Min Act: -0.0001

Data Index: 120569 (C4 (Web Text))

Max Activating Token Index: 117

Text #16

Max Range: 0.2992. Min Range: -0.2992

Max Act: 0.2134. Min Act: -0.0001

Data Index: 1025704 (C4 (Web Text))

Max Activating Token Index: 200

Text #17

Max Range: 0.2992. Min Range: -0.2992

Max Act: 0.2210. Min Act: -0.0001

Data Index: 745121 (C4 (Web Text))

Max Activating Token Index: 282

Text #18

Max Range: 0.2992. Min Range: -0.2992

Max Act: 0.2256. Min Act: -0.0001

Data Index: 1182415 (C4 (Web Text))

Max Activating Token Index: 540

Text #19

Max Range: 0.2992. Min Range: -0.2992

Max Act: 0.2294. Min Act: -0.0001

Data Index: 1383010 (Python Code)

Max Activating Token Index: 20