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

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

Neuron 2585 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: 0.1674. Min Range: -0.1674

Max Act: 0.1674. Min Act: -0.0004

Data Index: 149988 (C4 (Web Text))

Max Activating Token Index: 1002

Text #1

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1581. Min Act: -0.0004

Data Index: 339142 (C4 (Web Text))

Max Activating Token Index: 210

Text #2

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1456. Min Act: -0.0004

Data Index: 723677 (C4 (Web Text))

Max Activating Token Index: 809

Text #3

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1537. Min Act: -0.0004

Data Index: 39959 (C4 (Web Text))

Max Activating Token Index: 811

Text #4

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1362. Min Act: -0.0004

Data Index: 765580 (C4 (Web Text))

Max Activating Token Index: 336

Text #5

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1406. Min Act: -0.0004

Data Index: 946154 (C4 (Web Text))

Max Activating Token Index: 129

Text #6

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1244. Min Act: -0.0004

Data Index: 695612 (C4 (Web Text))

Max Activating Token Index: 835

Text #7

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1288. Min Act: -0.0004

Data Index: 906253 (C4 (Web Text))

Max Activating Token Index: 722

Text #8

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1279. Min Act: -0.0004

Data Index: 1313818 (C4 (Web Text))

Max Activating Token Index: 955

Text #9

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1310. Min Act: -0.0004

Data Index: 808461 (C4 (Web Text))

Max Activating Token Index: 292

Text #10

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1405. Min Act: -0.0004

Data Index: 619413 (C4 (Web Text))

Max Activating Token Index: 546

Text #11

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1272. Min Act: -0.0004

Data Index: 1055724 (C4 (Web Text))

Max Activating Token Index: 796

Text #12

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1237. Min Act: -0.0004

Data Index: 376783 (C4 (Web Text))

Max Activating Token Index: 830

Text #13

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1281. Min Act: -0.0004

Data Index: 592791 (C4 (Web Text))

Max Activating Token Index: 173

Text #14

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1196. Min Act: -0.0004

Data Index: 479896 (C4 (Web Text))

Max Activating Token Index: 83

Text #15

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1161. Min Act: -0.0004

Data Index: 550613 (C4 (Web Text))

Max Activating Token Index: 680

Text #16

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1234. Min Act: -0.0004

Data Index: 563210 (C4 (Web Text))

Max Activating Token Index: 982

Text #17

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1213. Min Act: -0.0004

Data Index: 1183012 (C4 (Web Text))

Max Activating Token Index: 765

Text #18

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1190. Min Act: -0.0004

Data Index: 380448 (C4 (Web Text))

Max Activating Token Index: 329

Text #19

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1162. Min Act: -0.0004

Data Index: 1271540 (C4 (Web Text))

Max Activating Token Index: 861