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

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

Neuron 1022 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0213. Min Act: -0.0005

Data Index: 1135394 (C4 (Web Text))

Max Activating Token Index: 157

Text #1

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0214. Min Act: -0.0005

Data Index: 296382 (C4 (Web Text))

Max Activating Token Index: 13

Text #2

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0207. Min Act: -0.0005

Data Index: 1273721 (C4 (Web Text))

Max Activating Token Index: 47

Text #3

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0205. Min Act: -0.0005

Data Index: 763455 (C4 (Web Text))

Max Activating Token Index: 857

Text #4

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0200. Min Act: -0.0005

Data Index: 263489 (C4 (Web Text))

Max Activating Token Index: 523

Text #5

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0196. Min Act: -0.0005

Data Index: 1574967 (Python Code)

Max Activating Token Index: 647

Text #6

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0195. Min Act: -0.0005

Data Index: 568905 (C4 (Web Text))

Max Activating Token Index: 882

Text #7

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0195. Min Act: -0.0005

Data Index: 1338372 (C4 (Web Text))

Max Activating Token Index: 835

Text #8

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0199. Min Act: -0.0005

Data Index: 1603462 (Python Code)

Max Activating Token Index: 143

Text #9

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0198. Min Act: -0.0005

Data Index: 144536 (C4 (Web Text))

Max Activating Token Index: 361

Text #10

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0198. Min Act: -0.0006

Data Index: 620637 (C4 (Web Text))

Max Activating Token Index: 856

Text #11

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0197. Min Act: -0.0005

Data Index: 745769 (C4 (Web Text))

Max Activating Token Index: 766

Text #12

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0193. Min Act: -0.0005

Data Index: 1239799 (C4 (Web Text))

Max Activating Token Index: 150

Text #13

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0192. Min Act: -0.0005

Data Index: 285386 (C4 (Web Text))

Max Activating Token Index: 39

Text #14

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0196. Min Act: -0.0005

Data Index: 1081354 (C4 (Web Text))

Max Activating Token Index: 155

Text #15

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0195. Min Act: -0.0005

Data Index: 1193948 (C4 (Web Text))

Max Activating Token Index: 298

Text #16

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0192. Min Act: -0.0005

Data Index: 1353467 (C4 (Web Text))

Max Activating Token Index: 259

Text #17

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0194. Min Act: -0.0005

Data Index: 372129 (C4 (Web Text))

Max Activating Token Index: 828

Text #18

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0189. Min Act: -0.0005

Data Index: 409540 (C4 (Web Text))

Max Activating Token Index: 436

Text #19

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0192. Min Act: -0.0005

Data Index: 779105 (C4 (Web Text))

Max Activating Token Index: 190