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

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

Neuron 2321 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: 0.0319. Min Range: -0.0319

Max Act: 0.0319. Min Act: -0.0002

Data Index: 1128557 (C4 (Web Text))

Max Activating Token Index: 479

Text #1

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0306. Min Act: -0.0002

Data Index: 1258497 (C4 (Web Text))

Max Activating Token Index: 330

Text #2

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0265. Min Act: -0.0002

Data Index: 61203 (C4 (Web Text))

Max Activating Token Index: 482

Text #3

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0288. Min Act: -0.0002

Data Index: 1213220 (C4 (Web Text))

Max Activating Token Index: 736

Text #4

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0267. Min Act: -0.0002

Data Index: 1145172 (C4 (Web Text))

Max Activating Token Index: 885

Text #5

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0242. Min Act: -0.0002

Data Index: 500806 (C4 (Web Text))

Max Activating Token Index: 838

Text #6

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0245. Min Act: -0.0002

Data Index: 209382 (C4 (Web Text))

Max Activating Token Index: 5

Text #7

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0231. Min Act: -0.0002

Data Index: 750910 (C4 (Web Text))

Max Activating Token Index: 487

Text #8

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0214. Min Act: -0.0002

Data Index: 719069 (C4 (Web Text))

Max Activating Token Index: 382

Text #9

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0211. Min Act: -0.0002

Data Index: 885988 (C4 (Web Text))

Max Activating Token Index: 867

Text #10

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0229. Min Act: -0.0002

Data Index: 1121884 (C4 (Web Text))

Max Activating Token Index: 886

Text #11

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0207. Min Act: -0.0002

Data Index: 1045128 (C4 (Web Text))

Max Activating Token Index: 408

Text #12

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0206. Min Act: -0.0002

Data Index: 152583 (C4 (Web Text))

Max Activating Token Index: 170

Text #13

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0216. Min Act: -0.0002

Data Index: 413802 (C4 (Web Text))

Max Activating Token Index: 38

Text #14

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0209. Min Act: -0.0002

Data Index: 760653 (C4 (Web Text))

Max Activating Token Index: 472

Text #15

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0219. Min Act: -0.0002

Data Index: 396595 (C4 (Web Text))

Max Activating Token Index: 72

Text #16

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0218. Min Act: -0.0002

Data Index: 1013300 (C4 (Web Text))

Max Activating Token Index: 352

Text #17

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0207. Min Act: -0.0002

Data Index: 1097412 (C4 (Web Text))

Max Activating Token Index: 164

Text #18

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0198. Min Act: -0.0002

Data Index: 132866 (C4 (Web Text))

Max Activating Token Index: 143

Text #19

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0204. Min Act: -0.0002

Data Index: 1142918 (C4 (Web Text))

Max Activating Token Index: 9