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

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

Neuron 2734 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0343. Min Act: -0.0000

Data Index: 499330 (C4 (Web Text))

Max Activating Token Index: 224

Text #1

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0220. Min Act: -0.0001

Data Index: 2441 (C4 (Web Text))

Max Activating Token Index: 314

Text #2

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0261. Min Act: -0.0001

Data Index: 1581939 (Python Code)

Max Activating Token Index: 834

Text #3

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0231. Min Act: -0.0000

Data Index: 278302 (C4 (Web Text))

Max Activating Token Index: 564

Text #4

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0224. Min Act: -0.0001

Data Index: 655889 (C4 (Web Text))

Max Activating Token Index: 996

Text #5

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0223. Min Act: -0.0001

Data Index: 818246 (C4 (Web Text))

Max Activating Token Index: 566

Text #6

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0200. Min Act: -0.0001

Data Index: 852864 (C4 (Web Text))

Max Activating Token Index: 762

Text #7

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0196. Min Act: -0.0001

Data Index: 978212 (C4 (Web Text))

Max Activating Token Index: 994

Text #8

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0205. Min Act: -0.0001

Data Index: 759018 (C4 (Web Text))

Max Activating Token Index: 993

Text #9

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0200. Min Act: -0.0001

Data Index: 326703 (C4 (Web Text))

Max Activating Token Index: 291

Text #10

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0221. Min Act: -0.0001

Data Index: 947838 (C4 (Web Text))

Max Activating Token Index: 244

Text #11

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0201. Min Act: -0.0001

Data Index: 1583996 (Python Code)

Max Activating Token Index: 577

Text #12

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0218. Min Act: -0.0001

Data Index: 377997 (C4 (Web Text))

Max Activating Token Index: 563

Text #13

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0201. Min Act: -0.0001

Data Index: 585092 (C4 (Web Text))

Max Activating Token Index: 627

Text #14

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0206. Min Act: -0.0001

Data Index: 1553389 (Python Code)

Max Activating Token Index: 376

Text #15

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0187. Min Act: -0.0001

Data Index: 1192857 (C4 (Web Text))

Max Activating Token Index: 912

Text #16

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0189. Min Act: -0.0000

Data Index: 815343 (C4 (Web Text))

Max Activating Token Index: 474

Text #17

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0195. Min Act: -0.0000

Data Index: 722321 (C4 (Web Text))

Max Activating Token Index: 990

Text #18

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0195. Min Act: -0.0001

Data Index: 513679 (C4 (Web Text))

Max Activating Token Index: 464

Text #19

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0194. Min Act: -0.0000

Data Index: 51378 (C4 (Web Text))

Max Activating Token Index: 114