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

Dataset: The Pile

Neuron 5077 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5038. Min Range: -0.5038

Max Act: 0.5038. Min Act: -0.0000

Data Index: 526050 (The Pile)

Max Activating Token Index: 855

Text #1

Max Range: 0.5038. Min Range: -0.5038

Max Act: 0.3560. Min Act: -0.0000

Data Index: 1669125 (The Pile)

Max Activating Token Index: 543

Text #2

Max Range: 0.5038. Min Range: -0.5038

Max Act: 0.4173. Min Act: -0.0000

Data Index: 1411236 (The Pile)

Max Activating Token Index: 192

Text #3

Max Range: 0.5038. Min Range: -0.5038

Max Act: 0.3445. Min Act: -0.0000

Data Index: 1857769 (The Pile)

Max Activating Token Index: 542

Text #4

Max Range: 0.5038. Min Range: -0.5038

Max Act: 0.3871. Min Act: -0.0000

Data Index: 224206 (The Pile)

Max Activating Token Index: 68

Text #5

Max Range: 0.5038. Min Range: -0.5038

Max Act: 0.3334. Min Act: -0.0000

Data Index: 1284384 (The Pile)

Max Activating Token Index: 89

Text #6

Max Range: 0.5038. Min Range: -0.5038

Max Act: 0.3757. Min Act: -0.0000

Data Index: 1725491 (The Pile)

Max Activating Token Index: 396

Text #7

Max Range: 0.5038. Min Range: -0.5038

Max Act: 0.3189. Min Act: -0.0000

Data Index: 405583 (The Pile)

Max Activating Token Index: 171

Text #8

Max Range: 0.5038. Min Range: -0.5038

Max Act: 0.3220. Min Act: -0.0000

Data Index: 1418608 (The Pile)

Max Activating Token Index: 420

Text #9

Max Range: 0.5038. Min Range: -0.5038

Max Act: 0.3368. Min Act: -0.0000

Data Index: 658084 (The Pile)

Max Activating Token Index: 525

Text #10

Max Range: 0.5038. Min Range: -0.5038

Max Act: 0.3316. Min Act: -0.0000

Data Index: 1525494 (The Pile)

Max Activating Token Index: 859

Text #11

Max Range: 0.5038. Min Range: -0.5038

Max Act: 0.3409. Min Act: -0.0000

Data Index: 1662780 (The Pile)

Max Activating Token Index: 786

Text #12

Max Range: 0.5038. Min Range: -0.5038

Max Act: 0.3175. Min Act: -0.0000

Data Index: 1311360 (The Pile)

Max Activating Token Index: 546

Text #13

Max Range: 0.5038. Min Range: -0.5038

Max Act: 0.3183. Min Act: -0.0000

Data Index: 461755 (The Pile)

Max Activating Token Index: 131

Text #14

Max Range: 0.5038. Min Range: -0.5038

Max Act: 0.3207. Min Act: -0.0000

Data Index: 15240 (The Pile)

Max Activating Token Index: 219

Text #15

Max Range: 0.5038. Min Range: -0.5038

Max Act: 0.3360. Min Act: -0.0000

Data Index: 786607 (The Pile)

Max Activating Token Index: 877

Text #16

Max Range: 0.5038. Min Range: -0.5038

Max Act: 0.3084. Min Act: -0.0000

Data Index: 494457 (The Pile)

Max Activating Token Index: 428

Text #17

Max Range: 0.5038. Min Range: -0.5038

Max Act: 0.3041. Min Act: 0.0000

Data Index: 198794 (The Pile)

Max Activating Token Index: 77

Text #18

Max Range: 0.5038. Min Range: -0.5038

Max Act: 0.3022. Min Act: -0.0000

Data Index: 709290 (The Pile)

Max Activating Token Index: 503

Text #19

Max Range: 0.5038. Min Range: -0.5038

Max Act: 0.3103. Min Act: -0.0000

Data Index: 361605 (The Pile)

Max Activating Token Index: 489