Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1206 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0270. Min Act: -0.0006

Data Index: 1409318 (Python Code)

Max Activating Token Index: 618

Text #1

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0273. Min Act: -0.0006

Data Index: 1554142 (Python Code)

Max Activating Token Index: 359

Text #2

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0270. Min Act: -0.0006

Data Index: 1482244 (Python Code)

Max Activating Token Index: 572

Text #3

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0248. Min Act: -0.0006

Data Index: 1283483 (C4 (Web Text))

Max Activating Token Index: 918

Text #4

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0251. Min Act: -0.0006

Data Index: 1461647 (Python Code)

Max Activating Token Index: 285

Text #5

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0249. Min Act: -0.0006

Data Index: 1649856 (Python Code)

Max Activating Token Index: 105

Text #6

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0249. Min Act: -0.0006

Data Index: 1546499 (Python Code)

Max Activating Token Index: 322

Text #7

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0239. Min Act: -0.0006

Data Index: 1368955 (Python Code)

Max Activating Token Index: 191

Text #8

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0236. Min Act: -0.0006

Data Index: 1213830 (C4 (Web Text))

Max Activating Token Index: 84

Text #9

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0220. Min Act: -0.0006

Data Index: 1345174 (C4 (Web Text))

Max Activating Token Index: 668

Text #10

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0239. Min Act: -0.0006

Data Index: 1413339 (Python Code)

Max Activating Token Index: 972

Text #11

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0243. Min Act: -0.0006

Data Index: 177662 (C4 (Web Text))

Max Activating Token Index: 143

Text #12

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0221. Min Act: -0.0006

Data Index: 634474 (C4 (Web Text))

Max Activating Token Index: 986

Text #13

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0225. Min Act: -0.0006

Data Index: 1034691 (C4 (Web Text))

Max Activating Token Index: 603

Text #14

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0227. Min Act: -0.0006

Data Index: 1133672 (C4 (Web Text))

Max Activating Token Index: 972

Text #15

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0233. Min Act: -0.0006

Data Index: 1606272 (Python Code)

Max Activating Token Index: 902

Text #16

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0232. Min Act: -0.0006

Data Index: 1526369 (Python Code)

Max Activating Token Index: 120

Text #17

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0227. Min Act: -0.0006

Data Index: 1548072 (Python Code)

Max Activating Token Index: 684

Text #18

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0227. Min Act: -0.0006

Data Index: 1333891 (C4 (Web Text))

Max Activating Token Index: 389

Text #19

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0216. Min Act: -0.0006

Data Index: 885142 (C4 (Web Text))

Max Activating Token Index: 375