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

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

Neuron 981 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0218. Min Act: -0.0003

Data Index: 984089 (C4 (Web Text))

Max Activating Token Index: 85

Text #1

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0221. Min Act: -0.0003

Data Index: 675107 (C4 (Web Text))

Max Activating Token Index: 105

Text #2

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0206. Min Act: -0.0003

Data Index: 1585451 (Python Code)

Max Activating Token Index: 227

Text #3

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0232. Min Act: -0.0003

Data Index: 240644 (C4 (Web Text))

Max Activating Token Index: 283

Text #4

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0213. Min Act: -0.0003

Data Index: 781599 (C4 (Web Text))

Max Activating Token Index: 730

Text #5

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0204. Min Act: -0.0003

Data Index: 486734 (C4 (Web Text))

Max Activating Token Index: 200

Text #6

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0221. Min Act: -0.0003

Data Index: 726770 (C4 (Web Text))

Max Activating Token Index: 795

Text #7

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0215. Min Act: -0.0003

Data Index: 229227 (C4 (Web Text))

Max Activating Token Index: 363

Text #8

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0188. Min Act: -0.0003

Data Index: 655610 (C4 (Web Text))

Max Activating Token Index: 204

Text #9

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0197. Min Act: -0.0003

Data Index: 28923 (C4 (Web Text))

Max Activating Token Index: 470

Text #10

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0207. Min Act: -0.0003

Data Index: 606669 (C4 (Web Text))

Max Activating Token Index: 239

Text #11

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0202. Min Act: -0.0003

Data Index: 993715 (C4 (Web Text))

Max Activating Token Index: 268

Text #12

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0188. Min Act: -0.0003

Data Index: 1375876 (Python Code)

Max Activating Token Index: 8

Text #13

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0195. Min Act: -0.0003

Data Index: 1283707 (C4 (Web Text))

Max Activating Token Index: 10

Text #14

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0183. Min Act: -0.0003

Data Index: 388938 (C4 (Web Text))

Max Activating Token Index: 339

Text #15

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0174. Min Act: -0.0003

Data Index: 598881 (C4 (Web Text))

Max Activating Token Index: 574

Text #16

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0187. Min Act: -0.0003

Data Index: 915805 (C4 (Web Text))

Max Activating Token Index: 51

Text #17

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0193. Min Act: -0.0003

Data Index: 2461 (C4 (Web Text))

Max Activating Token Index: 302

Text #18

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0193. Min Act: -0.0003

Data Index: 782395 (C4 (Web Text))

Max Activating Token Index: 207

Text #19

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0188. Min Act: -0.0003

Data Index: 1339312 (C4 (Web Text))

Max Activating Token Index: 404