Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 710 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0284. Min Act: -0.0006

Data Index: 592233 (C4 (Web Text))

Max Activating Token Index: 728

Text #1

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0239. Min Act: -0.0006

Data Index: 542959 (C4 (Web Text))

Max Activating Token Index: 528

Text #2

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0240. Min Act: -0.0005

Data Index: 1404982 (Python Code)

Max Activating Token Index: 406

Text #3

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0226. Min Act: -0.0006

Data Index: 433651 (C4 (Web Text))

Max Activating Token Index: 756

Text #4

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0225. Min Act: -0.0005

Data Index: 1479299 (Python Code)

Max Activating Token Index: 367

Text #5

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0223. Min Act: -0.0006

Data Index: 1484415 (Python Code)

Max Activating Token Index: 363

Text #6

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0210. Min Act: -0.0006

Data Index: 1070097 (C4 (Web Text))

Max Activating Token Index: 443

Text #7

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0211. Min Act: -0.0005

Data Index: 1360132 (Python Code)

Max Activating Token Index: 721

Text #8

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0211. Min Act: -0.0005

Data Index: 1585763 (Python Code)

Max Activating Token Index: 673

Text #9

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0205. Min Act: -0.0005

Data Index: 1405549 (Python Code)

Max Activating Token Index: 914

Text #10

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0200. Min Act: -0.0005

Data Index: 1591184 (Python Code)

Max Activating Token Index: 421

Text #11

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0206. Min Act: -0.0005

Data Index: 1491657 (Python Code)

Max Activating Token Index: 853

Text #12

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0203. Min Act: -0.0005

Data Index: 1637623 (Python Code)

Max Activating Token Index: 849

Text #13

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0202. Min Act: -0.0004

Data Index: 1572985 (Python Code)

Max Activating Token Index: 663

Text #14

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0199. Min Act: -0.0006

Data Index: 239571 (C4 (Web Text))

Max Activating Token Index: 935

Text #15

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0198. Min Act: -0.0005

Data Index: 1494994 (Python Code)

Max Activating Token Index: 416

Text #16

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0201. Min Act: -0.0005

Data Index: 1474851 (Python Code)

Max Activating Token Index: 900

Text #17

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0192. Min Act: -0.0005

Data Index: 1610596 (Python Code)

Max Activating Token Index: 459

Text #18

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0193. Min Act: -0.0006

Data Index: 75135 (C4 (Web Text))

Max Activating Token Index: 423

Text #19

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0191. Min Act: -0.0005

Data Index: 704317 (C4 (Web Text))

Max Activating Token Index: 471