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

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

Neuron 38 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: 0.0323. Min Range: -0.0323

Max Act: 0.0323. Min Act: -0.0004

Data Index: 266679 (C4 (Web Text))

Max Activating Token Index: 719

Text #1

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0298. Min Act: -0.0004

Data Index: 423683 (C4 (Web Text))

Max Activating Token Index: 948

Text #2

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0279. Min Act: -0.0004

Data Index: 243101 (C4 (Web Text))

Max Activating Token Index: 875

Text #3

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0243. Min Act: -0.0004

Data Index: 935675 (C4 (Web Text))

Max Activating Token Index: 321

Text #4

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0252. Min Act: -0.0004

Data Index: 194027 (C4 (Web Text))

Max Activating Token Index: 652

Text #5

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0252. Min Act: -0.0004

Data Index: 50111 (C4 (Web Text))

Max Activating Token Index: 646

Text #6

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0241. Min Act: -0.0004

Data Index: 568064 (C4 (Web Text))

Max Activating Token Index: 411

Text #7

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0227. Min Act: -0.0004

Data Index: 465984 (C4 (Web Text))

Max Activating Token Index: 236

Text #8

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0229. Min Act: -0.0004

Data Index: 271414 (C4 (Web Text))

Max Activating Token Index: 890

Text #9

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0242. Min Act: -0.0004

Data Index: 968302 (C4 (Web Text))

Max Activating Token Index: 1002

Text #10

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0232. Min Act: -0.0004

Data Index: 289692 (C4 (Web Text))

Max Activating Token Index: 882

Text #11

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0235. Min Act: -0.0004

Data Index: 584709 (C4 (Web Text))

Max Activating Token Index: 183

Text #12

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0253. Min Act: -0.0004

Data Index: 637704 (C4 (Web Text))

Max Activating Token Index: 844

Text #13

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0223. Min Act: -0.0004

Data Index: 1085980 (C4 (Web Text))

Max Activating Token Index: 992

Text #14

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0214. Min Act: -0.0004

Data Index: 1296064 (C4 (Web Text))

Max Activating Token Index: 996

Text #15

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0212. Min Act: -0.0004

Data Index: 363904 (C4 (Web Text))

Max Activating Token Index: 571

Text #16

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0221. Min Act: -0.0004

Data Index: 382932 (C4 (Web Text))

Max Activating Token Index: 12

Text #17

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0203. Min Act: -0.0004

Data Index: 707790 (C4 (Web Text))

Max Activating Token Index: 361

Text #18

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0213. Min Act: -0.0004

Data Index: 944425 (C4 (Web Text))

Max Activating Token Index: 1011

Text #19

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0203. Min Act: -0.0004

Data Index: 402073 (C4 (Web Text))

Max Activating Token Index: 819