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

Dataset: The Pile

Neuron 236 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: 0.5248. Min Range: -0.5248

Max Act: 0.5248. Min Act: -0.0000

Data Index: 800800 (The Pile)

Max Activating Token Index: 139

Text #1

Max Range: 0.5248. Min Range: -0.5248

Max Act: 0.4904. Min Act: -0.0000

Data Index: 1050385 (The Pile)

Max Activating Token Index: 138

Text #2

Max Range: 0.5248. Min Range: -0.5248

Max Act: 0.4682. Min Act: -0.0000

Data Index: 313550 (The Pile)

Max Activating Token Index: 953

Text #3

Max Range: 0.5248. Min Range: -0.5248

Max Act: 0.4246. Min Act: -0.0000

Data Index: 1722289 (The Pile)

Max Activating Token Index: 471

Text #4

Max Range: 0.5248. Min Range: -0.5248

Max Act: 0.3638. Min Act: -0.0000

Data Index: 1994623 (The Pile)

Max Activating Token Index: 411

Text #5

Max Range: 0.5248. Min Range: -0.5248

Max Act: 0.3870. Min Act: -0.0000

Data Index: 1170982 (The Pile)

Max Activating Token Index: 78

Text #6

Max Range: 0.5248. Min Range: -0.5248

Max Act: 0.3396. Min Act: -0.0000

Data Index: 1914093 (The Pile)

Max Activating Token Index: 622

Text #7

Max Range: 0.5248. Min Range: -0.5248

Max Act: 0.3138. Min Act: -0.0000

Data Index: 187915 (The Pile)

Max Activating Token Index: 633

Text #8

Max Range: 0.5248. Min Range: -0.5248

Max Act: 0.3584. Min Act: -0.0000

Data Index: 1611502 (The Pile)

Max Activating Token Index: 142

Text #9

Max Range: 0.5248. Min Range: -0.5248

Max Act: 0.3391. Min Act: -0.0000

Data Index: 1246450 (The Pile)

Max Activating Token Index: 899

Text #10

Max Range: 0.5248. Min Range: -0.5248

Max Act: 0.3292. Min Act: -0.0000

Data Index: 983706 (The Pile)

Max Activating Token Index: 859

Text #11

Max Range: 0.5248. Min Range: -0.5248

Max Act: 0.3356. Min Act: -0.0000

Data Index: 1315929 (The Pile)

Max Activating Token Index: 18

Text #12

Max Range: 0.5248. Min Range: -0.5248

Max Act: 0.3362. Min Act: -0.0000

Data Index: 1609067 (The Pile)

Max Activating Token Index: 416

Text #13

Max Range: 0.5248. Min Range: -0.5248

Max Act: 0.3081. Min Act: -0.0000

Data Index: 955661 (The Pile)

Max Activating Token Index: 509

Text #14

Max Range: 0.5248. Min Range: -0.5248

Max Act: 0.3303. Min Act: -0.0000

Data Index: 322486 (The Pile)

Max Activating Token Index: 667

Text #15

Max Range: 0.5248. Min Range: -0.5248

Max Act: 0.3175. Min Act: -0.0000

Data Index: 1706776 (The Pile)

Max Activating Token Index: 681

Text #16

Max Range: 0.5248. Min Range: -0.5248

Max Act: 0.3305. Min Act: -0.0000

Data Index: 1764514 (The Pile)

Max Activating Token Index: 574

Text #17

Max Range: 0.5248. Min Range: -0.5248

Max Act: 0.3258. Min Act: -0.0000

Data Index: 1540252 (The Pile)

Max Activating Token Index: 579

Text #18

Max Range: 0.5248. Min Range: -0.5248

Max Act: 0.3180. Min Act: -0.0000

Data Index: 1962052 (The Pile)

Max Activating Token Index: 440

Text #19

Max Range: 0.5248. Min Range: -0.5248

Max Act: 0.3462. Min Act: -0.0000

Data Index: 1640151 (The Pile)

Max Activating Token Index: 733