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

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

Neuron 4958 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: 0.0345. Min Range: -0.0345

Max Act: 0.0334. Min Act: -0.0002

Data Index: 1262866 (C4 (Web Text))

Max Activating Token Index: 351

Text #1

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0345. Min Act: -0.0002

Data Index: 972707 (C4 (Web Text))

Max Activating Token Index: 708

Text #2

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0295. Min Act: -0.0002

Data Index: 1158509 (C4 (Web Text))

Max Activating Token Index: 7

Text #3

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0301. Min Act: -0.0002

Data Index: 1220216 (C4 (Web Text))

Max Activating Token Index: 23

Text #4

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0297. Min Act: -0.0002

Data Index: 362725 (C4 (Web Text))

Max Activating Token Index: 404

Text #5

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0219. Min Act: -0.0002

Data Index: 1040226 (C4 (Web Text))

Max Activating Token Index: 258

Text #6

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0315. Min Act: -0.0002

Data Index: 387197 (C4 (Web Text))

Max Activating Token Index: 794

Text #7

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0270. Min Act: -0.0002

Data Index: 855519 (C4 (Web Text))

Max Activating Token Index: 145

Text #8

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0315. Min Act: -0.0002

Data Index: 1288201 (C4 (Web Text))

Max Activating Token Index: 641

Text #9

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0298. Min Act: -0.0002

Data Index: 1110141 (C4 (Web Text))

Max Activating Token Index: 328

Text #10

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0282. Min Act: -0.0002

Data Index: 699539 (C4 (Web Text))

Max Activating Token Index: 883

Text #11

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0246. Min Act: -0.0002

Data Index: 1188605 (C4 (Web Text))

Max Activating Token Index: 1008

Text #12

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0292. Min Act: -0.0002

Data Index: 1071392 (C4 (Web Text))

Max Activating Token Index: 271

Text #13

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0272. Min Act: -0.0002

Data Index: 372246 (C4 (Web Text))

Max Activating Token Index: 782

Text #14

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0245. Min Act: -0.0002

Data Index: 965110 (C4 (Web Text))

Max Activating Token Index: 347

Text #15

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0259. Min Act: -0.0002

Data Index: 156222 (C4 (Web Text))

Max Activating Token Index: 160

Text #16

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0260. Min Act: -0.0002

Data Index: 1015643 (C4 (Web Text))

Max Activating Token Index: 794

Text #17

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0247. Min Act: -0.0002

Data Index: 1105284 (C4 (Web Text))

Max Activating Token Index: 753

Text #18

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0229. Min Act: -0.0002

Data Index: 1172741 (C4 (Web Text))

Max Activating Token Index: 661

Text #19

Max Range: 0.0345. Min Range: -0.0345

Max Act: 0.0225. Min Act: -0.0002

Data Index: 641738 (C4 (Web Text))

Max Activating Token Index: 651