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

Dataset: The Pile

Neuron 163 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: 0.3361. Min Range: -0.3361

Max Act: 0.3361. Min Act: -0.0000

Data Index: 1806638 (The Pile)

Max Activating Token Index: 497

Text #1

Max Range: 0.3361. Min Range: -0.3361

Max Act: 0.2755. Min Act: -0.0000

Data Index: 167224 (The Pile)

Max Activating Token Index: 104

Text #2

Max Range: 0.3361. Min Range: -0.3361

Max Act: 0.2290. Min Act: -0.0000

Data Index: 558225 (The Pile)

Max Activating Token Index: 960

Text #3

Max Range: 0.3361. Min Range: -0.3361

Max Act: 0.2419. Min Act: -0.0000

Data Index: 137151 (The Pile)

Max Activating Token Index: 21

Text #4

Max Range: 0.3361. Min Range: -0.3361

Max Act: 0.2226. Min Act: -0.0000

Data Index: 1124411 (The Pile)

Max Activating Token Index: 314

Text #5

Max Range: 0.3361. Min Range: -0.3361

Max Act: 0.2428. Min Act: -0.0000

Data Index: 523456 (The Pile)

Max Activating Token Index: 798

Text #6

Max Range: 0.3361. Min Range: -0.3361

Max Act: 0.2239. Min Act: -0.0000

Data Index: 1917406 (The Pile)

Max Activating Token Index: 129

Text #7

Max Range: 0.3361. Min Range: -0.3361

Max Act: 0.2346. Min Act: -0.0000

Data Index: 1585281 (The Pile)

Max Activating Token Index: 19

Text #8

Max Range: 0.3361. Min Range: -0.3361

Max Act: 0.2236. Min Act: -0.0000

Data Index: 1031751 (The Pile)

Max Activating Token Index: 568

Text #9

Max Range: 0.3361. Min Range: -0.3361

Max Act: 0.1994. Min Act: -0.0000

Data Index: 1097399 (The Pile)

Max Activating Token Index: 397

Text #10

Max Range: 0.3361. Min Range: -0.3361

Max Act: 0.2153. Min Act: -0.0000

Data Index: 325567 (The Pile)

Max Activating Token Index: 773

Text #11

Max Range: 0.3361. Min Range: -0.3361

Max Act: 0.2309. Min Act: -0.0000

Data Index: 1061900 (The Pile)

Max Activating Token Index: 425

Text #12

Max Range: 0.3361. Min Range: -0.3361

Max Act: 0.2145. Min Act: -0.0000

Data Index: 1358166 (The Pile)

Max Activating Token Index: 1004

Text #13

Max Range: 0.3361. Min Range: -0.3361

Max Act: 0.2055. Min Act: -0.0000

Data Index: 1345579 (The Pile)

Max Activating Token Index: 67

Text #14

Max Range: 0.3361. Min Range: -0.3361

Max Act: 0.2108. Min Act: -0.0000

Data Index: 1058325 (The Pile)

Max Activating Token Index: 622

Text #15

Max Range: 0.3361. Min Range: -0.3361

Max Act: 0.1953. Min Act: -0.0000

Data Index: 1880128 (The Pile)

Max Activating Token Index: 136

Text #16

Max Range: 0.3361. Min Range: -0.3361

Max Act: 0.2415. Min Act: -0.0000

Data Index: 845075 (The Pile)

Max Activating Token Index: 914

Text #17

Max Range: 0.3361. Min Range: -0.3361

Max Act: 0.1898. Min Act: -0.0000

Data Index: 365390 (The Pile)

Max Activating Token Index: 240

Text #18

Max Range: 0.3361. Min Range: -0.3361

Max Act: 0.2198. Min Act: -0.0000

Data Index: 1192109 (The Pile)

Max Activating Token Index: 760

Text #19

Max Range: 0.3361. Min Range: -0.3361

Max Act: 0.2111. Min Act: -0.0000

Data Index: 691190 (The Pile)

Max Activating Token Index: 398