Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3110 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0240. Min Act: -0.0001

Data Index: 1138110 (C4 (Web Text))

Max Activating Token Index: 323

Text #1

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0241. Min Act: -0.0001

Data Index: 103959 (C4 (Web Text))

Max Activating Token Index: 380

Text #2

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0259. Min Act: -0.0001

Data Index: 1078925 (C4 (Web Text))

Max Activating Token Index: 334

Text #3

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0221. Min Act: -0.0001

Data Index: 488101 (C4 (Web Text))

Max Activating Token Index: 428

Text #4

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0217. Min Act: -0.0001

Data Index: 70062 (C4 (Web Text))

Max Activating Token Index: 284

Text #5

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0204. Min Act: -0.0001

Data Index: 32379 (C4 (Web Text))

Max Activating Token Index: 510

Text #6

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0183. Min Act: -0.0001

Data Index: 69353 (C4 (Web Text))

Max Activating Token Index: 378

Text #7

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0201. Min Act: -0.0001

Data Index: 1161144 (C4 (Web Text))

Max Activating Token Index: 295

Text #8

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0206. Min Act: -0.0001

Data Index: 1178114 (C4 (Web Text))

Max Activating Token Index: 962

Text #9

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0190. Min Act: -0.0001

Data Index: 371111 (C4 (Web Text))

Max Activating Token Index: 509

Text #10

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0193. Min Act: -0.0001

Data Index: 1359321 (C4 (Web Text))

Max Activating Token Index: 417

Text #11

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0190. Min Act: -0.0001

Data Index: 883909 (C4 (Web Text))

Max Activating Token Index: 919

Text #12

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0185. Min Act: -0.0001

Data Index: 1289646 (C4 (Web Text))

Max Activating Token Index: 320

Text #13

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0196. Min Act: -0.0001

Data Index: 1336258 (C4 (Web Text))

Max Activating Token Index: 376

Text #14

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0188. Min Act: -0.0001

Data Index: 380640 (C4 (Web Text))

Max Activating Token Index: 485

Text #15

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0182. Min Act: -0.0001

Data Index: 428271 (C4 (Web Text))

Max Activating Token Index: 355

Text #16

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0181. Min Act: -0.0001

Data Index: 305503 (C4 (Web Text))

Max Activating Token Index: 419

Text #17

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0178. Min Act: -0.0001

Data Index: 143288 (C4 (Web Text))

Max Activating Token Index: 1015

Text #18

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0182. Min Act: -0.0002

Data Index: 989894 (C4 (Web Text))

Max Activating Token Index: 1013

Text #19

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0180. Min Act: -0.0001

Data Index: 569237 (C4 (Web Text))

Max Activating Token Index: 733