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

Dataset: The Pile

Neuron 1559 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: 0.2897. Min Range: -0.2897

Max Act: 0.2897. Min Act: -0.0000

Data Index: 603285 (The Pile)

Max Activating Token Index: 557

Text #1

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.2560. Min Act: -0.0000

Data Index: 1819150 (The Pile)

Max Activating Token Index: 166

Text #2

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.2251. Min Act: -0.0000

Data Index: 1366877 (The Pile)

Max Activating Token Index: 807

Text #3

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.2387. Min Act: -0.0000

Data Index: 1157933 (The Pile)

Max Activating Token Index: 89

Text #4

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.2549. Min Act: -0.0000

Data Index: 1295727 (The Pile)

Max Activating Token Index: 601

Text #5

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.2052. Min Act: -0.0000

Data Index: 1256395 (The Pile)

Max Activating Token Index: 653

Text #6

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.2426. Min Act: -0.0000

Data Index: 1057456 (The Pile)

Max Activating Token Index: 245

Text #7

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.2312. Min Act: -0.0000

Data Index: 583819 (The Pile)

Max Activating Token Index: 948

Text #8

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.2137. Min Act: -0.0000

Data Index: 265552 (The Pile)

Max Activating Token Index: 427

Text #9

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.2213. Min Act: 0.0000

Data Index: 1361314 (The Pile)

Max Activating Token Index: 166

Text #10

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.2173. Min Act: -0.0000

Data Index: 1537139 (The Pile)

Max Activating Token Index: 609

Text #11

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.2238. Min Act: -0.0000

Data Index: 520494 (The Pile)

Max Activating Token Index: 825

Text #12

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.2077. Min Act: -0.0000

Data Index: 430542 (The Pile)

Max Activating Token Index: 640

Text #13

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.2207. Min Act: -0.0000

Data Index: 259426 (The Pile)

Max Activating Token Index: 145

Text #14

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.2123. Min Act: -0.0000

Data Index: 804277 (The Pile)

Max Activating Token Index: 341

Text #15

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.2180. Min Act: -0.0000

Data Index: 1795226 (The Pile)

Max Activating Token Index: 727

Text #16

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.2143. Min Act: -0.0000

Data Index: 433663 (The Pile)

Max Activating Token Index: 648

Text #17

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.2167. Min Act: -0.0000

Data Index: 49385 (The Pile)

Max Activating Token Index: 387

Text #18

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.1874. Min Act: -0.0000

Data Index: 1787068 (The Pile)

Max Activating Token Index: 663

Text #19

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.1983. Min Act: -0.0000

Data Index: 1481452 (The Pile)

Max Activating Token Index: 584