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

Dataset: The Pile

Neuron 3475 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: 0.3140. Min Range: -0.3140

Max Act: 0.3140. Min Act: -0.0000

Data Index: 1329090 (The Pile)

Max Activating Token Index: 564

Text #1

Max Range: 0.3140. Min Range: -0.3140

Max Act: 0.2693. Min Act: -0.0000

Data Index: 127515 (The Pile)

Max Activating Token Index: 37

Text #2

Max Range: 0.3140. Min Range: -0.3140

Max Act: 0.2447. Min Act: -0.0000

Data Index: 1014508 (The Pile)

Max Activating Token Index: 793

Text #3

Max Range: 0.3140. Min Range: -0.3140

Max Act: 0.2369. Min Act: -0.0000

Data Index: 933720 (The Pile)

Max Activating Token Index: 719

Text #4

Max Range: 0.3140. Min Range: -0.3140

Max Act: 0.2638. Min Act: -0.0000

Data Index: 161574 (The Pile)

Max Activating Token Index: 478

Text #5

Max Range: 0.3140. Min Range: -0.3140

Max Act: 0.2283. Min Act: 0.0000

Data Index: 1935894 (The Pile)

Max Activating Token Index: 798

Text #6

Max Range: 0.3140. Min Range: -0.3140

Max Act: 0.2314. Min Act: -0.0000

Data Index: 1727062 (The Pile)

Max Activating Token Index: 548

Text #7

Max Range: 0.3140. Min Range: -0.3140

Max Act: 0.2371. Min Act: 0.0000

Data Index: 1046624 (The Pile)

Max Activating Token Index: 611

Text #8

Max Range: 0.3140. Min Range: -0.3140

Max Act: 0.2322. Min Act: -0.0000

Data Index: 1592183 (The Pile)

Max Activating Token Index: 559

Text #9

Max Range: 0.3140. Min Range: -0.3140

Max Act: 0.2330. Min Act: 0.0000

Data Index: 1857927 (The Pile)

Max Activating Token Index: 771

Text #10

Max Range: 0.3140. Min Range: -0.3140

Max Act: 0.2354. Min Act: -0.0000

Data Index: 1586318 (The Pile)

Max Activating Token Index: 490

Text #11

Max Range: 0.3140. Min Range: -0.3140

Max Act: 0.2351. Min Act: -0.0000

Data Index: 607833 (The Pile)

Max Activating Token Index: 181

Text #12

Max Range: 0.3140. Min Range: -0.3140

Max Act: 0.2198. Min Act: -0.0000

Data Index: 216849 (The Pile)

Max Activating Token Index: 152

Text #13

Max Range: 0.3140. Min Range: -0.3140

Max Act: 0.2262. Min Act: -0.0000

Data Index: 865898 (The Pile)

Max Activating Token Index: 559

Text #14

Max Range: 0.3140. Min Range: -0.3140

Max Act: 0.2354. Min Act: -0.0000

Data Index: 726109 (The Pile)

Max Activating Token Index: 756

Text #15

Max Range: 0.3140. Min Range: -0.3140

Max Act: 0.2278. Min Act: -0.0000

Data Index: 852224 (The Pile)

Max Activating Token Index: 772

Text #16

Max Range: 0.3140. Min Range: -0.3140

Max Act: 0.2255. Min Act: -0.0000

Data Index: 586178 (The Pile)

Max Activating Token Index: 651

Text #17

Max Range: 0.3140. Min Range: -0.3140

Max Act: 0.2177. Min Act: -0.0000

Data Index: 1950476 (The Pile)

Max Activating Token Index: 879

Text #18

Max Range: 0.3140. Min Range: -0.3140

Max Act: 0.2025. Min Act: 0.0000

Data Index: 1872532 (The Pile)

Max Activating Token Index: 340

Text #19

Max Range: 0.3140. Min Range: -0.3140

Max Act: 0.2165. Min Act: -0.0000

Data Index: 535894 (The Pile)

Max Activating Token Index: 868