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

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

Neuron 245 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: 0.0327. Min Range: -0.0327

Max Act: 0.0327. Min Act: -0.0004

Data Index: 1382031 (Python Code)

Max Activating Token Index: 316

Text #1

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0289. Min Act: -0.0004

Data Index: 31861 (C4 (Web Text))

Max Activating Token Index: 449

Text #2

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0257. Min Act: -0.0004

Data Index: 289547 (C4 (Web Text))

Max Activating Token Index: 510

Text #3

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0233. Min Act: -0.0004

Data Index: 1193708 (C4 (Web Text))

Max Activating Token Index: 563

Text #4

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0257. Min Act: -0.0004

Data Index: 658682 (C4 (Web Text))

Max Activating Token Index: 494

Text #5

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0260. Min Act: -0.0004

Data Index: 1143756 (C4 (Web Text))

Max Activating Token Index: 243

Text #6

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0231. Min Act: -0.0004

Data Index: 530808 (C4 (Web Text))

Max Activating Token Index: 233

Text #7

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0249. Min Act: -0.0004

Data Index: 238697 (C4 (Web Text))

Max Activating Token Index: 305

Text #8

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0238. Min Act: -0.0004

Data Index: 1063071 (C4 (Web Text))

Max Activating Token Index: 109

Text #9

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0246. Min Act: -0.0004

Data Index: 679802 (C4 (Web Text))

Max Activating Token Index: 47

Text #10

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0222. Min Act: -0.0004

Data Index: 607204 (C4 (Web Text))

Max Activating Token Index: 839

Text #11

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0239. Min Act: -0.0004

Data Index: 413911 (C4 (Web Text))

Max Activating Token Index: 437

Text #12

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0216. Min Act: -0.0004

Data Index: 1003626 (C4 (Web Text))

Max Activating Token Index: 196

Text #13

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0244. Min Act: -0.0004

Data Index: 369423 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0240. Min Act: -0.0004

Data Index: 906730 (C4 (Web Text))

Max Activating Token Index: 160

Text #15

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0242. Min Act: -0.0004

Data Index: 895850 (C4 (Web Text))

Max Activating Token Index: 564

Text #16

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0216. Min Act: -0.0004

Data Index: 265821 (C4 (Web Text))

Max Activating Token Index: 318

Text #17

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0226. Min Act: -0.0004

Data Index: 735597 (C4 (Web Text))

Max Activating Token Index: 298

Text #18

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0239. Min Act: -0.0004

Data Index: 1472913 (Python Code)

Max Activating Token Index: 814

Text #19

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0241. Min Act: -0.0004

Data Index: 733647 (C4 (Web Text))

Max Activating Token Index: 796