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

Dataset: The Pile

Neuron 1965 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5417. Min Range: -0.5417

Max Act: 0.5417. Min Act: -0.0000

Data Index: 509398 (The Pile)

Max Activating Token Index: 76

Text #1

Max Range: 0.5417. Min Range: -0.5417

Max Act: 0.3943. Min Act: -0.0000

Data Index: 271624 (The Pile)

Max Activating Token Index: 259

Text #2

Max Range: 0.5417. Min Range: -0.5417

Max Act: 0.3633. Min Act: -0.0000

Data Index: 1040347 (The Pile)

Max Activating Token Index: 244

Text #3

Max Range: 0.5417. Min Range: -0.5417

Max Act: 0.3714. Min Act: -0.0000

Data Index: 1659340 (The Pile)

Max Activating Token Index: 371

Text #4

Max Range: 0.5417. Min Range: -0.5417

Max Act: 0.3623. Min Act: -0.0000

Data Index: 1128846 (The Pile)

Max Activating Token Index: 14

Text #5

Max Range: 0.5417. Min Range: -0.5417

Max Act: 0.3196. Min Act: -0.0000

Data Index: 593263 (The Pile)

Max Activating Token Index: 27

Text #6

Max Range: 0.5417. Min Range: -0.5417

Max Act: 0.3301. Min Act: -0.0000

Data Index: 380975 (The Pile)

Max Activating Token Index: 107

Text #7

Max Range: 0.5417. Min Range: -0.5417

Max Act: 0.3500. Min Act: -0.0000

Data Index: 592634 (The Pile)

Max Activating Token Index: 18

Text #8

Max Range: 0.5417. Min Range: -0.5417

Max Act: 0.3081. Min Act: -0.0000

Data Index: 1402568 (The Pile)

Max Activating Token Index: 534

Text #9

Max Range: 0.5417. Min Range: -0.5417

Max Act: 0.3153. Min Act: -0.0000

Data Index: 801124 (The Pile)

Max Activating Token Index: 53

Text #10

Max Range: 0.5417. Min Range: -0.5417

Max Act: 0.3248. Min Act: -0.0000

Data Index: 1086325 (The Pile)

Max Activating Token Index: 882

Text #11

Max Range: 0.5417. Min Range: -0.5417

Max Act: 0.2861. Min Act: -0.0000

Data Index: 404476 (The Pile)

Max Activating Token Index: 124

Text #12

Max Range: 0.5417. Min Range: -0.5417

Max Act: 0.3156. Min Act: -0.0000

Data Index: 448231 (The Pile)

Max Activating Token Index: 452

Text #13

Max Range: 0.5417. Min Range: -0.5417

Max Act: 0.3253. Min Act: -0.0000

Data Index: 255003 (The Pile)

Max Activating Token Index: 27

Text #14

Max Range: 0.5417. Min Range: -0.5417

Max Act: 0.3087. Min Act: -0.0000

Data Index: 947785 (The Pile)

Max Activating Token Index: 554

Text #15

Max Range: 0.5417. Min Range: -0.5417

Max Act: 0.3000. Min Act: -0.0000

Data Index: 1377282 (The Pile)

Max Activating Token Index: 450

Text #16

Max Range: 0.5417. Min Range: -0.5417

Max Act: 0.3060. Min Act: -0.0000

Data Index: 1836802 (The Pile)

Max Activating Token Index: 576

Text #17

Max Range: 0.5417. Min Range: -0.5417

Max Act: 0.2859. Min Act: -0.0000

Data Index: 476523 (The Pile)

Max Activating Token Index: 50

Text #18

Max Range: 0.5417. Min Range: -0.5417

Max Act: 0.3066. Min Act: -0.0000

Data Index: 1006256 (The Pile)

Max Activating Token Index: 227

Text #19

Max Range: 0.5417. Min Range: -0.5417

Max Act: 0.2944. Min Act: -0.0000

Data Index: 930331 (The Pile)

Max Activating Token Index: 29