Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1214 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0263. Min Act: -0.0006

Data Index: 320310 (C4 (Web Text))

Max Activating Token Index: 34

Text #1

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0255. Min Act: -0.0006

Data Index: 722856 (C4 (Web Text))

Max Activating Token Index: 39

Text #2

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0255. Min Act: -0.0006

Data Index: 1271048 (C4 (Web Text))

Max Activating Token Index: 210

Text #3

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0254. Min Act: -0.0006

Data Index: 1225452 (C4 (Web Text))

Max Activating Token Index: 746

Text #4

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0242. Min Act: -0.0006

Data Index: 793728 (C4 (Web Text))

Max Activating Token Index: 453

Text #5

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0247. Min Act: -0.0006

Data Index: 665662 (C4 (Web Text))

Max Activating Token Index: 27

Text #6

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0235. Min Act: -0.0006

Data Index: 1046866 (C4 (Web Text))

Max Activating Token Index: 870

Text #7

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0235. Min Act: -0.0006

Data Index: 753707 (C4 (Web Text))

Max Activating Token Index: 36

Text #8

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0236. Min Act: -0.0006

Data Index: 880244 (C4 (Web Text))

Max Activating Token Index: 96

Text #9

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0229. Min Act: -0.0006

Data Index: 1217377 (C4 (Web Text))

Max Activating Token Index: 51

Text #10

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0229. Min Act: -0.0006

Data Index: 1287619 (C4 (Web Text))

Max Activating Token Index: 81

Text #11

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0228. Min Act: -0.0006

Data Index: 1033196 (C4 (Web Text))

Max Activating Token Index: 38

Text #12

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0218. Min Act: -0.0006

Data Index: 114596 (C4 (Web Text))

Max Activating Token Index: 464

Text #13

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0205. Min Act: -0.0006

Data Index: 876045 (C4 (Web Text))

Max Activating Token Index: 1011

Text #14

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0222. Min Act: -0.0006

Data Index: 878040 (C4 (Web Text))

Max Activating Token Index: 884

Text #15

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0206. Min Act: -0.0006

Data Index: 1088591 (C4 (Web Text))

Max Activating Token Index: 851

Text #16

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0225. Min Act: -0.0006

Data Index: 1456331 (Python Code)

Max Activating Token Index: 10

Text #17

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0218. Min Act: -0.0006

Data Index: 190432 (C4 (Web Text))

Max Activating Token Index: 28

Text #18

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0213. Min Act: -0.0006

Data Index: 413626 (C4 (Web Text))

Max Activating Token Index: 899

Text #19

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0217. Min Act: -0.0006

Data Index: 609539 (C4 (Web Text))

Max Activating Token Index: 214