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

Dataset: The Pile

Neuron 2790 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2893. Min Range: -1.2893

Max Act: 1.2893. Min Act: -0.0000

Data Index: 692097 (The Pile)

Max Activating Token Index: 186

Text #1

Max Range: 1.2893. Min Range: -1.2893

Max Act: 1.2828. Min Act: -0.0000

Data Index: 1193048 (The Pile)

Max Activating Token Index: 431

Text #2

Max Range: 1.2893. Min Range: -1.2893

Max Act: 1.2205. Min Act: -0.0000

Data Index: 1896513 (The Pile)

Max Activating Token Index: 765

Text #3

Max Range: 1.2893. Min Range: -1.2893

Max Act: 1.1463. Min Act: -0.0000

Data Index: 1490689 (The Pile)

Max Activating Token Index: 489

Text #4

Max Range: 1.2893. Min Range: -1.2893

Max Act: 1.0647. Min Act: -0.0000

Data Index: 1446551 (The Pile)

Max Activating Token Index: 591

Text #5

Max Range: 1.2893. Min Range: -1.2893

Max Act: 1.0903. Min Act: -0.0000

Data Index: 958602 (The Pile)

Max Activating Token Index: 951

Text #6

Max Range: 1.2893. Min Range: -1.2893

Max Act: 1.1235. Min Act: -0.0000

Data Index: 1426967 (The Pile)

Max Activating Token Index: 165

Text #7

Max Range: 1.2893. Min Range: -1.2893

Max Act: 1.0709. Min Act: -0.0000

Data Index: 1970012 (The Pile)

Max Activating Token Index: 391

Text #8

Max Range: 1.2893. Min Range: -1.2893

Max Act: 1.0429. Min Act: -0.0000

Data Index: 1225583 (The Pile)

Max Activating Token Index: 203

Text #9

Max Range: 1.2893. Min Range: -1.2893

Max Act: 0.9675. Min Act: -0.0000

Data Index: 1691561 (The Pile)

Max Activating Token Index: 628

Text #10

Max Range: 1.2893. Min Range: -1.2893

Max Act: 0.9650. Min Act: -0.0000

Data Index: 500328 (The Pile)

Max Activating Token Index: 455

Text #11

Max Range: 1.2893. Min Range: -1.2893

Max Act: 0.9459. Min Act: -0.0000

Data Index: 431204 (The Pile)

Max Activating Token Index: 794

Text #12

Max Range: 1.2893. Min Range: -1.2893

Max Act: 1.0308. Min Act: -0.0000

Data Index: 377471 (The Pile)

Max Activating Token Index: 760

Text #13

Max Range: 1.2893. Min Range: -1.2893

Max Act: 0.9199. Min Act: -0.0000

Data Index: 1937575 (The Pile)

Max Activating Token Index: 58

Text #14

Max Range: 1.2893. Min Range: -1.2893

Max Act: 0.9450. Min Act: -0.0000

Data Index: 1943468 (The Pile)

Max Activating Token Index: 176

Text #15

Max Range: 1.2893. Min Range: -1.2893

Max Act: 0.9220. Min Act: -0.0000

Data Index: 262259 (The Pile)

Max Activating Token Index: 131

Text #16

Max Range: 1.2893. Min Range: -1.2893

Max Act: 0.9189. Min Act: -0.0000

Data Index: 1960562 (The Pile)

Max Activating Token Index: 490

Text #17

Max Range: 1.2893. Min Range: -1.2893

Max Act: 0.8787. Min Act: -0.0000

Data Index: 315114 (The Pile)

Max Activating Token Index: 956

Text #18

Max Range: 1.2893. Min Range: -1.2893

Max Act: 0.8759. Min Act: -0.0000

Data Index: 1262441 (The Pile)

Max Activating Token Index: 869

Text #19

Max Range: 1.2893. Min Range: -1.2893

Max Act: 0.9346. Min Act: -0.0000

Data Index: 1028218 (The Pile)

Max Activating Token Index: 949