Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3156 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0483. Min Act: -0.0002

Data Index: 542019 (C4 (Web Text))

Max Activating Token Index: 49

Text #1

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0387. Min Act: -0.0002

Data Index: 1246323 (C4 (Web Text))

Max Activating Token Index: 891

Text #2

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0421. Min Act: -0.0002

Data Index: 1116198 (C4 (Web Text))

Max Activating Token Index: 35

Text #3

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0376. Min Act: -0.0002

Data Index: 525507 (C4 (Web Text))

Max Activating Token Index: 940

Text #4

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0319. Min Act: -0.0002

Data Index: 629613 (C4 (Web Text))

Max Activating Token Index: 325

Text #5

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0360. Min Act: -0.0002

Data Index: 1273532 (C4 (Web Text))

Max Activating Token Index: 14

Text #6

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0340. Min Act: -0.0002

Data Index: 906279 (C4 (Web Text))

Max Activating Token Index: 516

Text #7

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0357. Min Act: -0.0002

Data Index: 124096 (C4 (Web Text))

Max Activating Token Index: 84

Text #8

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0338. Min Act: -0.0002

Data Index: 186883 (C4 (Web Text))

Max Activating Token Index: 331

Text #9

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0348. Min Act: -0.0002

Data Index: 369089 (C4 (Web Text))

Max Activating Token Index: 755

Text #10

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0335. Min Act: -0.0002

Data Index: 250178 (C4 (Web Text))

Max Activating Token Index: 994

Text #11

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0309. Min Act: -0.0002

Data Index: 763263 (C4 (Web Text))

Max Activating Token Index: 974

Text #12

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0290. Min Act: -0.0002

Data Index: 258645 (C4 (Web Text))

Max Activating Token Index: 586

Text #13

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0275. Min Act: -0.0002

Data Index: 452035 (C4 (Web Text))

Max Activating Token Index: 147

Text #14

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0339. Min Act: -0.0002

Data Index: 518756 (C4 (Web Text))

Max Activating Token Index: 404

Text #15

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0302. Min Act: -0.0002

Data Index: 105552 (C4 (Web Text))

Max Activating Token Index: 127

Text #16

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0315. Min Act: -0.0002

Data Index: 427169 (C4 (Web Text))

Max Activating Token Index: 121

Text #17

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0285. Min Act: -0.0002

Data Index: 57112 (C4 (Web Text))

Max Activating Token Index: 627

Text #18

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0275. Min Act: -0.0002

Data Index: 1143974 (C4 (Web Text))

Max Activating Token Index: 61

Text #19

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0257. Min Act: -0.0002

Data Index: 114861 (C4 (Web Text))

Max Activating Token Index: 748