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

Dataset: The Pile

Neuron 2991 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: 0.3405. Min Range: -0.3405

Max Act: 0.3405. Min Act: -0.0000

Data Index: 1128066 (The Pile)

Max Activating Token Index: 580

Text #1

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.3186. Min Act: -0.0000

Data Index: 475850 (The Pile)

Max Activating Token Index: 432

Text #2

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.3218. Min Act: -0.0000

Data Index: 1971847 (The Pile)

Max Activating Token Index: 917

Text #3

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.2925. Min Act: -0.0000

Data Index: 162086 (The Pile)

Max Activating Token Index: 992

Text #4

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.2866. Min Act: -0.0000

Data Index: 529994 (The Pile)

Max Activating Token Index: 710

Text #5

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.2628. Min Act: -0.0000

Data Index: 1605244 (The Pile)

Max Activating Token Index: 40

Text #6

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.2763. Min Act: -0.0000

Data Index: 1441918 (The Pile)

Max Activating Token Index: 259

Text #7

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.2435. Min Act: -0.0000

Data Index: 522562 (The Pile)

Max Activating Token Index: 519

Text #8

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.2604. Min Act: -0.0000

Data Index: 853394 (The Pile)

Max Activating Token Index: 329

Text #9

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.2584. Min Act: -0.0000

Data Index: 1032423 (The Pile)

Max Activating Token Index: 315

Text #10

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.2290. Min Act: -0.0000

Data Index: 734243 (The Pile)

Max Activating Token Index: 1006

Text #11

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.2522. Min Act: -0.0000

Data Index: 759301 (The Pile)

Max Activating Token Index: 30

Text #12

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.2350. Min Act: -0.0000

Data Index: 650506 (The Pile)

Max Activating Token Index: 602

Text #13

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.2200. Min Act: -0.0000

Data Index: 408581 (The Pile)

Max Activating Token Index: 851

Text #14

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.2363. Min Act: -0.0000

Data Index: 1700277 (The Pile)

Max Activating Token Index: 197

Text #15

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.2168. Min Act: -0.0000

Data Index: 1582778 (The Pile)

Max Activating Token Index: 470

Text #16

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.2291. Min Act: -0.0000

Data Index: 715245 (The Pile)

Max Activating Token Index: 266

Text #17

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.2213. Min Act: -0.0000

Data Index: 51717 (The Pile)

Max Activating Token Index: 208

Text #18

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.2246. Min Act: -0.0000

Data Index: 68002 (The Pile)

Max Activating Token Index: 859

Text #19

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.2177. Min Act: -0.0000

Data Index: 681372 (The Pile)

Max Activating Token Index: 31