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

Dataset: The Pile

Neuron 4443 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2323. Min Range: -5.2323

Max Act: 4.9449. Min Act: -0.0000

Data Index: 1082675 (The Pile)

Max Activating Token Index: 464

Text #1

Max Range: 5.2323. Min Range: -5.2323

Max Act: 5.2323. Min Act: -0.0000

Data Index: 156967 (The Pile)

Max Activating Token Index: 563

Text #2

Max Range: 5.2323. Min Range: -5.2323

Max Act: 4.2925. Min Act: -0.0000

Data Index: 59010 (The Pile)

Max Activating Token Index: 181

Text #3

Max Range: 5.2323. Min Range: -5.2323

Max Act: 4.4520. Min Act: -0.0000

Data Index: 1209706 (The Pile)

Max Activating Token Index: 199

Text #4

Max Range: 5.2323. Min Range: -5.2323

Max Act: 4.1376. Min Act: -0.0000

Data Index: 1660825 (The Pile)

Max Activating Token Index: 474

Text #5

Max Range: 5.2323. Min Range: -5.2323

Max Act: 3.8663. Min Act: -0.0000

Data Index: 465218 (The Pile)

Max Activating Token Index: 557

Text #6

Max Range: 5.2323. Min Range: -5.2323

Max Act: 3.7730. Min Act: -0.0000

Data Index: 215527 (The Pile)

Max Activating Token Index: 354

Text #7

Max Range: 5.2323. Min Range: -5.2323

Max Act: 3.6826. Min Act: -0.0000

Data Index: 158971 (The Pile)

Max Activating Token Index: 797

Text #8

Max Range: 5.2323. Min Range: -5.2323

Max Act: 3.6291. Min Act: -0.0000

Data Index: 948744 (The Pile)

Max Activating Token Index: 337

Text #9

Max Range: 5.2323. Min Range: -5.2323

Max Act: 3.6012. Min Act: -0.0000

Data Index: 1311248 (The Pile)

Max Activating Token Index: 189

Text #10

Max Range: 5.2323. Min Range: -5.2323

Max Act: 3.6025. Min Act: -0.0000

Data Index: 466391 (The Pile)

Max Activating Token Index: 818

Text #11

Max Range: 5.2323. Min Range: -5.2323

Max Act: 3.5667. Min Act: -0.0000

Data Index: 871214 (The Pile)

Max Activating Token Index: 201

Text #12

Max Range: 5.2323. Min Range: -5.2323

Max Act: 3.5084. Min Act: -0.0000

Data Index: 532460 (The Pile)

Max Activating Token Index: 109

Text #13

Max Range: 5.2323. Min Range: -5.2323

Max Act: 3.6378. Min Act: -0.0000

Data Index: 1292349 (The Pile)

Max Activating Token Index: 953

Text #14

Max Range: 5.2323. Min Range: -5.2323

Max Act: 3.3348. Min Act: -0.0000

Data Index: 1951339 (The Pile)

Max Activating Token Index: 276

Text #15

Max Range: 5.2323. Min Range: -5.2323

Max Act: 3.3221. Min Act: -0.0000

Data Index: 665283 (The Pile)

Max Activating Token Index: 151

Text #16

Max Range: 5.2323. Min Range: -5.2323

Max Act: 3.3148. Min Act: -0.0000

Data Index: 256253 (The Pile)

Max Activating Token Index: 258

Text #17

Max Range: 5.2323. Min Range: -5.2323

Max Act: 3.3935. Min Act: -0.0000

Data Index: 388266 (The Pile)

Max Activating Token Index: 775

Text #18

Max Range: 5.2323. Min Range: -5.2323

Max Act: 3.2427. Min Act: -0.0000

Data Index: 1319768 (The Pile)

Max Activating Token Index: 467

Text #19

Max Range: 5.2323. Min Range: -5.2323

Max Act: 3.2112. Min Act: -0.0000

Data Index: 1556254 (The Pile)

Max Activating Token Index: 254