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

Dataset: The Pile

Neuron 2570 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4184. Min Range: -0.4184

Max Act: 0.4184. Min Act: -0.0000

Data Index: 1744049 (The Pile)

Max Activating Token Index: 442

Text #1

Max Range: 0.4184. Min Range: -0.4184

Max Act: 0.3846. Min Act: -0.0000

Data Index: 694238 (The Pile)

Max Activating Token Index: 613

Text #2

Max Range: 0.4184. Min Range: -0.4184

Max Act: 0.3548. Min Act: -0.0000

Data Index: 1543790 (The Pile)

Max Activating Token Index: 967

Text #3

Max Range: 0.4184. Min Range: -0.4184

Max Act: 0.3781. Min Act: -0.0000

Data Index: 1982947 (The Pile)

Max Activating Token Index: 233

Text #4

Max Range: 0.4184. Min Range: -0.4184

Max Act: 0.3830. Min Act: -0.0000

Data Index: 834669 (The Pile)

Max Activating Token Index: 86

Text #5

Max Range: 0.4184. Min Range: -0.4184

Max Act: 0.3922. Min Act: -0.0000

Data Index: 1749696 (The Pile)

Max Activating Token Index: 529

Text #6

Max Range: 0.4184. Min Range: -0.4184

Max Act: 0.3877. Min Act: -0.0000

Data Index: 1345528 (The Pile)

Max Activating Token Index: 726

Text #7

Max Range: 0.4184. Min Range: -0.4184

Max Act: 0.3457. Min Act: -0.0000

Data Index: 287707 (The Pile)

Max Activating Token Index: 490

Text #8

Max Range: 0.4184. Min Range: -0.4184

Max Act: 0.3477. Min Act: -0.0000

Data Index: 120138 (The Pile)

Max Activating Token Index: 585

Text #9

Max Range: 0.4184. Min Range: -0.4184

Max Act: 0.3404. Min Act: -0.0000

Data Index: 542317 (The Pile)

Max Activating Token Index: 109

Text #10

Max Range: 0.4184. Min Range: -0.4184

Max Act: 0.3161. Min Act: -0.0000

Data Index: 50995 (The Pile)

Max Activating Token Index: 615

Text #11

Max Range: 0.4184. Min Range: -0.4184

Max Act: 0.3332. Min Act: -0.0000

Data Index: 1924662 (The Pile)

Max Activating Token Index: 319

Text #12

Max Range: 0.4184. Min Range: -0.4184

Max Act: 0.3293. Min Act: -0.0000

Data Index: 1145549 (The Pile)

Max Activating Token Index: 297

Text #13

Max Range: 0.4184. Min Range: -0.4184

Max Act: 0.3217. Min Act: -0.0000

Data Index: 1436627 (The Pile)

Max Activating Token Index: 448

Text #14

Max Range: 0.4184. Min Range: -0.4184

Max Act: 0.3317. Min Act: -0.0000

Data Index: 911103 (The Pile)

Max Activating Token Index: 730

Text #15

Max Range: 0.4184. Min Range: -0.4184

Max Act: 0.3419. Min Act: -0.0000

Data Index: 65543 (The Pile)

Max Activating Token Index: 183

Text #16

Max Range: 0.4184. Min Range: -0.4184

Max Act: 0.3155. Min Act: -0.0000

Data Index: 1024802 (The Pile)

Max Activating Token Index: 851

Text #17

Max Range: 0.4184. Min Range: -0.4184

Max Act: 0.3156. Min Act: -0.0000

Data Index: 828932 (The Pile)

Max Activating Token Index: 238

Text #18

Max Range: 0.4184. Min Range: -0.4184

Max Act: 0.3047. Min Act: -0.0000

Data Index: 1181762 (The Pile)

Max Activating Token Index: 470

Text #19

Max Range: 0.4184. Min Range: -0.4184

Max Act: 0.3060. Min Act: -0.0000

Data Index: 1916648 (The Pile)

Max Activating Token Index: 376