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

Dataset: The Pile

Neuron 2633 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3226. Min Range: -0.3226

Max Act: 0.3226. Min Act: -0.0000

Data Index: 1999687 (The Pile)

Max Activating Token Index: 197

Text #1

Max Range: 0.3226. Min Range: -0.3226

Max Act: 0.3054. Min Act: -0.0000

Data Index: 972480 (The Pile)

Max Activating Token Index: 601

Text #2

Max Range: 0.3226. Min Range: -0.3226

Max Act: 0.2820. Min Act: -0.0000

Data Index: 551169 (The Pile)

Max Activating Token Index: 57

Text #3

Max Range: 0.3226. Min Range: -0.3226

Max Act: 0.2925. Min Act: -0.0000

Data Index: 1731210 (The Pile)

Max Activating Token Index: 1013

Text #4

Max Range: 0.3226. Min Range: -0.3226

Max Act: 0.2544. Min Act: -0.0000

Data Index: 567063 (The Pile)

Max Activating Token Index: 387

Text #5

Max Range: 0.3226. Min Range: -0.3226

Max Act: 0.2582. Min Act: -0.0000

Data Index: 1533121 (The Pile)

Max Activating Token Index: 455

Text #6

Max Range: 0.3226. Min Range: -0.3226

Max Act: 0.2529. Min Act: -0.0000

Data Index: 94400 (The Pile)

Max Activating Token Index: 622

Text #7

Max Range: 0.3226. Min Range: -0.3226

Max Act: 0.2239. Min Act: -0.0000

Data Index: 751219 (The Pile)

Max Activating Token Index: 409

Text #8

Max Range: 0.3226. Min Range: -0.3226

Max Act: 0.2500. Min Act: -0.0000

Data Index: 407639 (The Pile)

Max Activating Token Index: 296

Text #9

Max Range: 0.3226. Min Range: -0.3226

Max Act: 0.2319. Min Act: -0.0000

Data Index: 729149 (The Pile)

Max Activating Token Index: 968

Text #10

Max Range: 0.3226. Min Range: -0.3226

Max Act: 0.2187. Min Act: -0.0000

Data Index: 98417 (The Pile)

Max Activating Token Index: 465

Text #11

Max Range: 0.3226. Min Range: -0.3226

Max Act: 0.2311. Min Act: -0.0000

Data Index: 797785 (The Pile)

Max Activating Token Index: 1021

Text #12

Max Range: 0.3226. Min Range: -0.3226

Max Act: 0.2152. Min Act: -0.0000

Data Index: 1849819 (The Pile)

Max Activating Token Index: 939

Text #13

Max Range: 0.3226. Min Range: -0.3226

Max Act: 0.2166. Min Act: -0.0000

Data Index: 586267 (The Pile)

Max Activating Token Index: 782

Text #14

Max Range: 0.3226. Min Range: -0.3226

Max Act: 0.2053. Min Act: -0.0000

Data Index: 1099915 (The Pile)

Max Activating Token Index: 1010

Text #15

Max Range: 0.3226. Min Range: -0.3226

Max Act: 0.2418. Min Act: -0.0000

Data Index: 529274 (The Pile)

Max Activating Token Index: 588

Text #16

Max Range: 0.3226. Min Range: -0.3226

Max Act: 0.2057. Min Act: -0.0000

Data Index: 695325 (The Pile)

Max Activating Token Index: 427

Text #17

Max Range: 0.3226. Min Range: -0.3226

Max Act: 0.2026. Min Act: -0.0000

Data Index: 1704627 (The Pile)

Max Activating Token Index: 267

Text #18

Max Range: 0.3226. Min Range: -0.3226

Max Act: 0.1971. Min Act: -0.0000

Data Index: 1262654 (The Pile)

Max Activating Token Index: 981

Text #19

Max Range: 0.3226. Min Range: -0.3226

Max Act: 0.2018. Min Act: -0.0000

Data Index: 1943688 (The Pile)

Max Activating Token Index: 478