Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 459 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.8229. Min Range: -1.8229

Max Act: 1.8229. Min Act: -0.0000

Data Index: 341550 (The Pile)

Max Activating Token Index: 171

Text #1

Max Range: 1.8229. Min Range: -1.8229

Max Act: 1.6948. Min Act: -0.0000

Data Index: 632278 (The Pile)

Max Activating Token Index: 462

Text #2

Max Range: 1.8229. Min Range: -1.8229

Max Act: 1.5412. Min Act: -0.0000

Data Index: 800062 (The Pile)

Max Activating Token Index: 779

Text #3

Max Range: 1.8229. Min Range: -1.8229

Max Act: 1.4290. Min Act: -0.0000

Data Index: 1331169 (The Pile)

Max Activating Token Index: 397

Text #4

Max Range: 1.8229. Min Range: -1.8229

Max Act: 1.3210. Min Act: -0.0000

Data Index: 945353 (The Pile)

Max Activating Token Index: 295

Text #5

Max Range: 1.8229. Min Range: -1.8229

Max Act: 1.3284. Min Act: -0.0000

Data Index: 1873977 (The Pile)

Max Activating Token Index: 748

Text #6

Max Range: 1.8229. Min Range: -1.8229

Max Act: 1.2201. Min Act: -0.0000

Data Index: 297468 (The Pile)

Max Activating Token Index: 146

Text #7

Max Range: 1.8229. Min Range: -1.8229

Max Act: 1.2821. Min Act: -0.0000

Data Index: 1143949 (The Pile)

Max Activating Token Index: 411

Text #8

Max Range: 1.8229. Min Range: -1.8229

Max Act: 1.2331. Min Act: -0.0000

Data Index: 553949 (The Pile)

Max Activating Token Index: 269

Text #9

Max Range: 1.8229. Min Range: -1.8229

Max Act: 1.2212. Min Act: -0.0000

Data Index: 1214404 (The Pile)

Max Activating Token Index: 844

Text #10

Max Range: 1.8229. Min Range: -1.8229

Max Act: 1.1565. Min Act: -0.0000

Data Index: 645235 (The Pile)

Max Activating Token Index: 241

Text #11

Max Range: 1.8229. Min Range: -1.8229

Max Act: 1.1932. Min Act: -0.0000

Data Index: 1567204 (The Pile)

Max Activating Token Index: 398

Text #12

Max Range: 1.8229. Min Range: -1.8229

Max Act: 1.2913. Min Act: -0.0000

Data Index: 1773783 (The Pile)

Max Activating Token Index: 784

Text #13

Max Range: 1.8229. Min Range: -1.8229

Max Act: 1.1343. Min Act: -0.0000

Data Index: 1084711 (The Pile)

Max Activating Token Index: 481

Text #14

Max Range: 1.8229. Min Range: -1.8229

Max Act: 1.2425. Min Act: -0.0000

Data Index: 1429850 (The Pile)

Max Activating Token Index: 48

Text #15

Max Range: 1.8229. Min Range: -1.8229

Max Act: 1.2897. Min Act: -0.0000

Data Index: 1333806 (The Pile)

Max Activating Token Index: 615

Text #16

Max Range: 1.8229. Min Range: -1.8229

Max Act: 1.1582. Min Act: -0.0000

Data Index: 429849 (The Pile)

Max Activating Token Index: 62

Text #17

Max Range: 1.8229. Min Range: -1.8229

Max Act: 1.1381. Min Act: -0.0000

Data Index: 998858 (The Pile)

Max Activating Token Index: 266

Text #18

Max Range: 1.8229. Min Range: -1.8229

Max Act: 1.0943. Min Act: -0.0000

Data Index: 178315 (The Pile)

Max Activating Token Index: 27

Text #19

Max Range: 1.8229. Min Range: -1.8229

Max Act: 1.1888. Min Act: -0.0000

Data Index: 1039897 (The Pile)

Max Activating Token Index: 78