Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 3353 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.8239. Min Range: -0.8239

Max Act: 0.8239. Min Act: -0.0000

Data Index: 603310 (The Pile)

Max Activating Token Index: 755

Text #1

Max Range: 0.8239. Min Range: -0.8239

Max Act: 0.7371. Min Act: -0.0000

Data Index: 1305589 (The Pile)

Max Activating Token Index: 42

Text #2

Max Range: 0.8239. Min Range: -0.8239

Max Act: 0.6338. Min Act: -0.0000

Data Index: 1737357 (The Pile)

Max Activating Token Index: 164

Text #3

Max Range: 0.8239. Min Range: -0.8239

Max Act: 0.5968. Min Act: -0.0000

Data Index: 29320 (The Pile)

Max Activating Token Index: 416

Text #4

Max Range: 0.8239. Min Range: -0.8239

Max Act: 0.6124. Min Act: -0.0000

Data Index: 569973 (The Pile)

Max Activating Token Index: 70

Text #5

Max Range: 0.8239. Min Range: -0.8239

Max Act: 0.6038. Min Act: -0.0000

Data Index: 808157 (The Pile)

Max Activating Token Index: 540

Text #6

Max Range: 0.8239. Min Range: -0.8239

Max Act: 0.5832. Min Act: -0.0000

Data Index: 991946 (The Pile)

Max Activating Token Index: 172

Text #7

Max Range: 0.8239. Min Range: -0.8239

Max Act: 0.5471. Min Act: -0.0000

Data Index: 388403 (The Pile)

Max Activating Token Index: 158

Text #8

Max Range: 0.8239. Min Range: -0.8239

Max Act: 0.5448. Min Act: -0.0000

Data Index: 1553880 (The Pile)

Max Activating Token Index: 378

Text #9

Max Range: 0.8239. Min Range: -0.8239

Max Act: 0.5497. Min Act: -0.0000

Data Index: 1778922 (The Pile)

Max Activating Token Index: 1012

Text #10

Max Range: 0.8239. Min Range: -0.8239

Max Act: 0.5599. Min Act: -0.0000

Data Index: 581680 (The Pile)

Max Activating Token Index: 326

Text #11

Max Range: 0.8239. Min Range: -0.8239

Max Act: 0.5911. Min Act: -0.0000

Data Index: 638720 (The Pile)

Max Activating Token Index: 54

Text #12

Max Range: 0.8239. Min Range: -0.8239

Max Act: 0.5596. Min Act: -0.0000

Data Index: 736393 (The Pile)

Max Activating Token Index: 994

Text #13

Max Range: 0.8239. Min Range: -0.8239

Max Act: 0.5289. Min Act: -0.0000

Data Index: 628424 (The Pile)

Max Activating Token Index: 1015

Text #14

Max Range: 0.8239. Min Range: -0.8239

Max Act: 0.5376. Min Act: -0.0000

Data Index: 241101 (The Pile)

Max Activating Token Index: 966

Text #15

Max Range: 0.8239. Min Range: -0.8239

Max Act: 0.5236. Min Act: -0.0000

Data Index: 812439 (The Pile)

Max Activating Token Index: 661

Text #16

Max Range: 0.8239. Min Range: -0.8239

Max Act: 0.5050. Min Act: -0.0000

Data Index: 143146 (The Pile)

Max Activating Token Index: 640

Text #17

Max Range: 0.8239. Min Range: -0.8239

Max Act: 0.5428. Min Act: -0.0000

Data Index: 1427750 (The Pile)

Max Activating Token Index: 455

Text #18

Max Range: 0.8239. Min Range: -0.8239

Max Act: 0.5211. Min Act: -0.0000

Data Index: 1157714 (The Pile)

Max Activating Token Index: 257

Text #19

Max Range: 0.8239. Min Range: -0.8239

Max Act: 0.5358. Min Act: -0.0000

Data Index: 541478 (The Pile)

Max Activating Token Index: 383