Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1504 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0242. Min Act: -0.0004

Data Index: 1600121 (Python Code)

Max Activating Token Index: 6

Text #1

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0245. Min Act: -0.0004

Data Index: 1195173 (C4 (Web Text))

Max Activating Token Index: 3

Text #2

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0225. Min Act: -0.0004

Data Index: 582745 (C4 (Web Text))

Max Activating Token Index: 910

Text #3

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0215. Min Act: -0.0004

Data Index: 85414 (C4 (Web Text))

Max Activating Token Index: 960

Text #4

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0242. Min Act: -0.0004

Data Index: 1166571 (C4 (Web Text))

Max Activating Token Index: 835

Text #5

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0237. Min Act: -0.0004

Data Index: 597492 (C4 (Web Text))

Max Activating Token Index: 16

Text #6

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0235. Min Act: -0.0004

Data Index: 1343306 (C4 (Web Text))

Max Activating Token Index: 649

Text #7

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0220. Min Act: -0.0004

Data Index: 1611294 (Python Code)

Max Activating Token Index: 466

Text #8

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0190. Min Act: -0.0004

Data Index: 1144408 (C4 (Web Text))

Max Activating Token Index: 783

Text #9

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0211. Min Act: -0.0004

Data Index: 96327 (C4 (Web Text))

Max Activating Token Index: 286

Text #10

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0220. Min Act: -0.0004

Data Index: 507155 (C4 (Web Text))

Max Activating Token Index: 29

Text #11

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0229. Min Act: -0.0004

Data Index: 493215 (C4 (Web Text))

Max Activating Token Index: 55

Text #12

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0218. Min Act: -0.0004

Data Index: 611273 (C4 (Web Text))

Max Activating Token Index: 193

Text #13

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0223. Min Act: -0.0004

Data Index: 1539920 (Python Code)

Max Activating Token Index: 972

Text #14

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0223. Min Act: -0.0004

Data Index: 1325552 (C4 (Web Text))

Max Activating Token Index: 661

Text #15

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0225. Min Act: -0.0004

Data Index: 1580875 (Python Code)

Max Activating Token Index: 6

Text #16

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0230. Min Act: -0.0004

Data Index: 242826 (C4 (Web Text))

Max Activating Token Index: 793

Text #17

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0235. Min Act: -0.0004

Data Index: 187377 (C4 (Web Text))

Max Activating Token Index: 948

Text #18

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0220. Min Act: -0.0004

Data Index: 177972 (C4 (Web Text))

Max Activating Token Index: 914

Text #19

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0219. Min Act: -0.0004

Data Index: 1492436 (Python Code)

Max Activating Token Index: 1002