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

Dataset: The Pile

Neuron 2246 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8066. Min Range: -1.8066

Max Act: 1.8066. Min Act: -0.0000

Data Index: 1278121 (The Pile)

Max Activating Token Index: 931

Text #1

Max Range: 1.8066. Min Range: -1.8066

Max Act: 1.4149. Min Act: -0.0000

Data Index: 600906 (The Pile)

Max Activating Token Index: 786

Text #2

Max Range: 1.8066. Min Range: -1.8066

Max Act: 1.5659. Min Act: -0.0000

Data Index: 742018 (The Pile)

Max Activating Token Index: 210

Text #3

Max Range: 1.8066. Min Range: -1.8066

Max Act: 1.4412. Min Act: -0.0000

Data Index: 697173 (The Pile)

Max Activating Token Index: 150

Text #4

Max Range: 1.8066. Min Range: -1.8066

Max Act: 1.4508. Min Act: -0.0000

Data Index: 1988782 (The Pile)

Max Activating Token Index: 735

Text #5

Max Range: 1.8066. Min Range: -1.8066

Max Act: 1.5895. Min Act: -0.0000

Data Index: 752395 (The Pile)

Max Activating Token Index: 885

Text #6

Max Range: 1.8066. Min Range: -1.8066

Max Act: 1.5416. Min Act: -0.0000

Data Index: 323562 (The Pile)

Max Activating Token Index: 408

Text #7

Max Range: 1.8066. Min Range: -1.8066

Max Act: 1.4385. Min Act: -0.0000

Data Index: 974710 (The Pile)

Max Activating Token Index: 109

Text #8

Max Range: 1.8066. Min Range: -1.8066

Max Act: 1.4067. Min Act: -0.0000

Data Index: 1282011 (The Pile)

Max Activating Token Index: 83

Text #9

Max Range: 1.8066. Min Range: -1.8066

Max Act: 1.4548. Min Act: -0.0000

Data Index: 1061284 (The Pile)

Max Activating Token Index: 505

Text #10

Max Range: 1.8066. Min Range: -1.8066

Max Act: 1.3266. Min Act: -0.0000

Data Index: 1484167 (The Pile)

Max Activating Token Index: 64

Text #11

Max Range: 1.8066. Min Range: -1.8066

Max Act: 1.4705. Min Act: -0.0000

Data Index: 1091120 (The Pile)

Max Activating Token Index: 127

Text #12

Max Range: 1.8066. Min Range: -1.8066

Max Act: 1.4286. Min Act: -0.0000

Data Index: 97244 (The Pile)

Max Activating Token Index: 318

Text #13

Max Range: 1.8066. Min Range: -1.8066

Max Act: 1.4362. Min Act: -0.0000

Data Index: 74101 (The Pile)

Max Activating Token Index: 338

Text #14

Max Range: 1.8066. Min Range: -1.8066

Max Act: 1.5336. Min Act: -0.0000

Data Index: 1662835 (The Pile)

Max Activating Token Index: 202

Text #15

Max Range: 1.8066. Min Range: -1.8066

Max Act: 1.3393. Min Act: -0.0000

Data Index: 523748 (The Pile)

Max Activating Token Index: 159

Text #16

Max Range: 1.8066. Min Range: -1.8066

Max Act: 1.3336. Min Act: -0.0000

Data Index: 1154945 (The Pile)

Max Activating Token Index: 688

Text #17

Max Range: 1.8066. Min Range: -1.8066

Max Act: 1.3036. Min Act: -0.0000

Data Index: 265703 (The Pile)

Max Activating Token Index: 232

Text #18

Max Range: 1.8066. Min Range: -1.8066

Max Act: 1.3039. Min Act: -0.0000

Data Index: 744975 (The Pile)

Max Activating Token Index: 414

Text #19

Max Range: 1.8066. Min Range: -1.8066

Max Act: 1.3216. Min Act: -0.0000

Data Index: 1972498 (The Pile)

Max Activating Token Index: 321