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

Dataset: The Pile

Neuron 1809 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: 0.4325. Min Range: -0.4325

Max Act: 0.4325. Min Act: -0.0000

Data Index: 413815 (The Pile)

Max Activating Token Index: 765

Text #1

Max Range: 0.4325. Min Range: -0.4325

Max Act: 0.4262. Min Act: -0.0000

Data Index: 1021376 (The Pile)

Max Activating Token Index: 284

Text #2

Max Range: 0.4325. Min Range: -0.4325

Max Act: 0.4064. Min Act: -0.0000

Data Index: 1972555 (The Pile)

Max Activating Token Index: 703

Text #3

Max Range: 0.4325. Min Range: -0.4325

Max Act: 0.3773. Min Act: -0.0000

Data Index: 577194 (The Pile)

Max Activating Token Index: 99

Text #4

Max Range: 0.4325. Min Range: -0.4325

Max Act: 0.3569. Min Act: -0.0000

Data Index: 486957 (The Pile)

Max Activating Token Index: 62

Text #5

Max Range: 0.4325. Min Range: -0.4325

Max Act: 0.3747. Min Act: -0.0000

Data Index: 1178954 (The Pile)

Max Activating Token Index: 362

Text #6

Max Range: 0.4325. Min Range: -0.4325

Max Act: 0.3436. Min Act: -0.0000

Data Index: 961267 (The Pile)

Max Activating Token Index: 574

Text #7

Max Range: 0.4325. Min Range: -0.4325

Max Act: 0.3465. Min Act: -0.0000

Data Index: 554532 (The Pile)

Max Activating Token Index: 934

Text #8

Max Range: 0.4325. Min Range: -0.4325

Max Act: 0.3552. Min Act: -0.0000

Data Index: 332408 (The Pile)

Max Activating Token Index: 376

Text #9

Max Range: 0.4325. Min Range: -0.4325

Max Act: 0.3615. Min Act: -0.0000

Data Index: 236989 (The Pile)

Max Activating Token Index: 820

Text #10

Max Range: 0.4325. Min Range: -0.4325

Max Act: 0.3490. Min Act: -0.0000

Data Index: 993638 (The Pile)

Max Activating Token Index: 926

Text #11

Max Range: 0.4325. Min Range: -0.4325

Max Act: 0.3425. Min Act: -0.0000

Data Index: 1353227 (The Pile)

Max Activating Token Index: 636

Text #12

Max Range: 0.4325. Min Range: -0.4325

Max Act: 0.3156. Min Act: -0.0000

Data Index: 813575 (The Pile)

Max Activating Token Index: 849

Text #13

Max Range: 0.4325. Min Range: -0.4325

Max Act: 0.3255. Min Act: -0.0000

Data Index: 257589 (The Pile)

Max Activating Token Index: 152

Text #14

Max Range: 0.4325. Min Range: -0.4325

Max Act: 0.3086. Min Act: -0.0000

Data Index: 1988806 (The Pile)

Max Activating Token Index: 998

Text #15

Max Range: 0.4325. Min Range: -0.4325

Max Act: 0.3220. Min Act: -0.0000

Data Index: 1987987 (The Pile)

Max Activating Token Index: 155

Text #16

Max Range: 0.4325. Min Range: -0.4325

Max Act: 0.3296. Min Act: -0.0000

Data Index: 640277 (The Pile)

Max Activating Token Index: 298

Text #17

Max Range: 0.4325. Min Range: -0.4325

Max Act: 0.3408. Min Act: -0.0000

Data Index: 1473444 (The Pile)

Max Activating Token Index: 728

Text #18

Max Range: 0.4325. Min Range: -0.4325

Max Act: 0.3173. Min Act: -0.0000

Data Index: 1850872 (The Pile)

Max Activating Token Index: 336

Text #19

Max Range: 0.4325. Min Range: -0.4325

Max Act: 0.3127. Min Act: -0.0000

Data Index: 1862714 (The Pile)

Max Activating Token Index: 662