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

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

Neuron 2946 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0417. Min Act: -0.0002

Data Index: 272973 (C4 (Web Text))

Max Activating Token Index: 24

Text #1

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0352. Min Act: -0.0002

Data Index: 391065 (C4 (Web Text))

Max Activating Token Index: 638

Text #2

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0322. Min Act: -0.0002

Data Index: 1091589 (C4 (Web Text))

Max Activating Token Index: 14

Text #3

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0305. Min Act: -0.0002

Data Index: 154242 (C4 (Web Text))

Max Activating Token Index: 340

Text #4

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0260. Min Act: -0.0002

Data Index: 170204 (C4 (Web Text))

Max Activating Token Index: 784

Text #5

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0285. Min Act: -0.0002

Data Index: 987186 (C4 (Web Text))

Max Activating Token Index: 72

Text #6

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0255. Min Act: -0.0002

Data Index: 979211 (C4 (Web Text))

Max Activating Token Index: 54

Text #7

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0278. Min Act: -0.0002

Data Index: 696699 (C4 (Web Text))

Max Activating Token Index: 247

Text #8

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0268. Min Act: -0.0002

Data Index: 755835 (C4 (Web Text))

Max Activating Token Index: 73

Text #9

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0229. Min Act: -0.0002

Data Index: 1165827 (C4 (Web Text))

Max Activating Token Index: 165

Text #10

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0263. Min Act: -0.0002

Data Index: 1197207 (C4 (Web Text))

Max Activating Token Index: 970

Text #11

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0257. Min Act: -0.0002

Data Index: 647404 (C4 (Web Text))

Max Activating Token Index: 267

Text #12

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0262. Min Act: -0.0002

Data Index: 538954 (C4 (Web Text))

Max Activating Token Index: 10

Text #13

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0271. Min Act: -0.0002

Data Index: 469699 (C4 (Web Text))

Max Activating Token Index: 17

Text #14

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0244. Min Act: -0.0002

Data Index: 415518 (C4 (Web Text))

Max Activating Token Index: 483

Text #15

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0247. Min Act: -0.0002

Data Index: 707164 (C4 (Web Text))

Max Activating Token Index: 395

Text #16

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0269. Min Act: -0.0002

Data Index: 990711 (C4 (Web Text))

Max Activating Token Index: 121

Text #17

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0239. Min Act: -0.0002

Data Index: 68116 (C4 (Web Text))

Max Activating Token Index: 201

Text #18

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0207. Min Act: -0.0002

Data Index: 239196 (C4 (Web Text))

Max Activating Token Index: 980

Text #19

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0250. Min Act: -0.0002

Data Index: 792940 (C4 (Web Text))

Max Activating Token Index: 395