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

Dataset: The Pile

Neuron 3060 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: 0.2592. Min Range: -0.2592

Max Act: 0.2592. Min Act: -0.0000

Data Index: 181855 (The Pile)

Max Activating Token Index: 389

Text #1

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.2508. Min Act: -0.0000

Data Index: 895409 (The Pile)

Max Activating Token Index: 421

Text #2

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.2450. Min Act: -0.0000

Data Index: 1072702 (The Pile)

Max Activating Token Index: 253

Text #3

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.2422. Min Act: -0.0000

Data Index: 1867341 (The Pile)

Max Activating Token Index: 1009

Text #4

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.2439. Min Act: -0.0000

Data Index: 1108535 (The Pile)

Max Activating Token Index: 353

Text #5

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.2330. Min Act: -0.0000

Data Index: 1477617 (The Pile)

Max Activating Token Index: 693

Text #6

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.2265. Min Act: -0.0000

Data Index: 686696 (The Pile)

Max Activating Token Index: 739

Text #7

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.2355. Min Act: -0.0000

Data Index: 921467 (The Pile)

Max Activating Token Index: 1009

Text #8

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.2292. Min Act: -0.0000

Data Index: 1427054 (The Pile)

Max Activating Token Index: 614

Text #9

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.2194. Min Act: -0.0000

Data Index: 1708012 (The Pile)

Max Activating Token Index: 987

Text #10

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.2263. Min Act: -0.0000

Data Index: 1026211 (The Pile)

Max Activating Token Index: 1010

Text #11

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.2231. Min Act: -0.0000

Data Index: 707762 (The Pile)

Max Activating Token Index: 969

Text #12

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.2157. Min Act: -0.0000

Data Index: 1571263 (The Pile)

Max Activating Token Index: 626

Text #13

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.2309. Min Act: -0.0000

Data Index: 1486273 (The Pile)

Max Activating Token Index: 197

Text #14

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.2227. Min Act: -0.0000

Data Index: 713562 (The Pile)

Max Activating Token Index: 277

Text #15

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.2191. Min Act: -0.0000

Data Index: 1905339 (The Pile)

Max Activating Token Index: 197

Text #16

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.2230. Min Act: -0.0000

Data Index: 475054 (The Pile)

Max Activating Token Index: 593

Text #17

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.2156. Min Act: -0.0000

Data Index: 714759 (The Pile)

Max Activating Token Index: 520

Text #18

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.2167. Min Act: 0.0000

Data Index: 1019010 (The Pile)

Max Activating Token Index: 786

Text #19

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.2120. Min Act: -0.0000

Data Index: 1117076 (The Pile)

Max Activating Token Index: 611