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

Dataset: The Pile

Neuron 1179 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 10.6419. Min Range: -10.6419

Max Act: 10.4941. Min Act: -0.0000

Data Index: 1379850 (The Pile)

Max Activating Token Index: 405

Text #1

Max Range: 10.6419. Min Range: -10.6419

Max Act: 10.4377. Min Act: -0.0000

Data Index: 1710334 (The Pile)

Max Activating Token Index: 854

Text #2

Max Range: 10.6419. Min Range: -10.6419

Max Act: 9.9578. Min Act: -0.0000

Data Index: 411900 (The Pile)

Max Activating Token Index: 647

Text #3

Max Range: 10.6419. Min Range: -10.6419

Max Act: 10.5813. Min Act: -0.0000

Data Index: 172637 (The Pile)

Max Activating Token Index: 444

Text #4

Max Range: 10.6419. Min Range: -10.6419

Max Act: 10.3000. Min Act: -0.0000

Data Index: 366731 (The Pile)

Max Activating Token Index: 446

Text #5

Max Range: 10.6419. Min Range: -10.6419

Max Act: 10.2582. Min Act: -0.0000

Data Index: 1739522 (The Pile)

Max Activating Token Index: 462

Text #6

Max Range: 10.6419. Min Range: -10.6419

Max Act: 10.1026. Min Act: -0.0000

Data Index: 1872370 (The Pile)

Max Activating Token Index: 616

Text #7

Max Range: 10.6419. Min Range: -10.6419

Max Act: 10.6419. Min Act: -0.0000

Data Index: 35980 (The Pile)

Max Activating Token Index: 193

Text #8

Max Range: 10.6419. Min Range: -10.6419

Max Act: 10.1468. Min Act: -0.0000

Data Index: 840642 (The Pile)

Max Activating Token Index: 701

Text #9

Max Range: 10.6419. Min Range: -10.6419

Max Act: 10.1333. Min Act: -0.0000

Data Index: 1948438 (The Pile)

Max Activating Token Index: 344

Text #10

Max Range: 10.6419. Min Range: -10.6419

Max Act: 9.9770. Min Act: -0.0000

Data Index: 372205 (The Pile)

Max Activating Token Index: 585

Text #11

Max Range: 10.6419. Min Range: -10.6419

Max Act: 10.2408. Min Act: -0.0001

Data Index: 1439599 (The Pile)

Max Activating Token Index: 421

Text #12

Max Range: 10.6419. Min Range: -10.6419

Max Act: 10.2212. Min Act: -0.0000

Data Index: 1388734 (The Pile)

Max Activating Token Index: 372

Text #13

Max Range: 10.6419. Min Range: -10.6419

Max Act: 10.0626. Min Act: -0.0000

Data Index: 1123249 (The Pile)

Max Activating Token Index: 399

Text #14

Max Range: 10.6419. Min Range: -10.6419

Max Act: 10.1038. Min Act: -0.0000

Data Index: 786462 (The Pile)

Max Activating Token Index: 298

Text #15

Max Range: 10.6419. Min Range: -10.6419

Max Act: 9.9757. Min Act: -0.0000

Data Index: 935382 (The Pile)

Max Activating Token Index: 228

Text #16

Max Range: 10.6419. Min Range: -10.6419

Max Act: 10.3805. Min Act: -0.0000

Data Index: 566130 (The Pile)

Max Activating Token Index: 230

Text #17

Max Range: 10.6419. Min Range: -10.6419

Max Act: 10.2096. Min Act: -0.0000

Data Index: 1958411 (The Pile)

Max Activating Token Index: 378

Text #18

Max Range: 10.6419. Min Range: -10.6419

Max Act: 10.0878. Min Act: -0.0000

Data Index: 1575878 (The Pile)

Max Activating Token Index: 342

Text #19

Max Range: 10.6419. Min Range: -10.6419

Max Act: 10.0750. Min Act: -0.0000

Data Index: 713863 (The Pile)

Max Activating Token Index: 442