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

Dataset: The Pile

Neuron 2688 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6239. Min Range: -0.6239

Max Act: 0.6239. Min Act: -0.0000

Data Index: 1713300 (The Pile)

Max Activating Token Index: 772

Text #1

Max Range: 0.6239. Min Range: -0.6239

Max Act: 0.6222. Min Act: -0.0000

Data Index: 1790581 (The Pile)

Max Activating Token Index: 727

Text #2

Max Range: 0.6239. Min Range: -0.6239

Max Act: 0.5864. Min Act: -0.0000

Data Index: 463688 (The Pile)

Max Activating Token Index: 509

Text #3

Max Range: 0.6239. Min Range: -0.6239

Max Act: 0.5759. Min Act: -0.0000

Data Index: 1888258 (The Pile)

Max Activating Token Index: 365

Text #4

Max Range: 0.6239. Min Range: -0.6239

Max Act: 0.5736. Min Act: -0.0000

Data Index: 525145 (The Pile)

Max Activating Token Index: 197

Text #5

Max Range: 0.6239. Min Range: -0.6239

Max Act: 0.5693. Min Act: -0.0000

Data Index: 1055095 (The Pile)

Max Activating Token Index: 757

Text #6

Max Range: 0.6239. Min Range: -0.6239

Max Act: 0.5677. Min Act: -0.0000

Data Index: 308028 (The Pile)

Max Activating Token Index: 248

Text #7

Max Range: 0.6239. Min Range: -0.6239

Max Act: 0.5588. Min Act: -0.0000

Data Index: 1662063 (The Pile)

Max Activating Token Index: 936

Text #8

Max Range: 0.6239. Min Range: -0.6239

Max Act: 0.5253. Min Act: -0.0000

Data Index: 184811 (The Pile)

Max Activating Token Index: 448

Text #9

Max Range: 0.6239. Min Range: -0.6239

Max Act: 0.5368. Min Act: -0.0000

Data Index: 1799116 (The Pile)

Max Activating Token Index: 617

Text #10

Max Range: 0.6239. Min Range: -0.6239

Max Act: 0.5558. Min Act: -0.0000

Data Index: 1971462 (The Pile)

Max Activating Token Index: 798

Text #11

Max Range: 0.6239. Min Range: -0.6239

Max Act: 0.5275. Min Act: -0.0000

Data Index: 1758276 (The Pile)

Max Activating Token Index: 795

Text #12

Max Range: 0.6239. Min Range: -0.6239

Max Act: 0.5240. Min Act: -0.0000

Data Index: 1484446 (The Pile)

Max Activating Token Index: 476

Text #13

Max Range: 0.6239. Min Range: -0.6239

Max Act: 0.4902. Min Act: -0.0000

Data Index: 1250541 (The Pile)

Max Activating Token Index: 6

Text #14

Max Range: 0.6239. Min Range: -0.6239

Max Act: 0.5033. Min Act: -0.0000

Data Index: 428353 (The Pile)

Max Activating Token Index: 922

Text #15

Max Range: 0.6239. Min Range: -0.6239

Max Act: 0.5524. Min Act: -0.0000

Data Index: 805626 (The Pile)

Max Activating Token Index: 475

Text #16

Max Range: 0.6239. Min Range: -0.6239

Max Act: 0.5165. Min Act: -0.0000

Data Index: 629896 (The Pile)

Max Activating Token Index: 560

Text #17

Max Range: 0.6239. Min Range: -0.6239

Max Act: 0.4966. Min Act: -0.0000

Data Index: 1044498 (The Pile)

Max Activating Token Index: 59

Text #18

Max Range: 0.6239. Min Range: -0.6239

Max Act: 0.4918. Min Act: -0.0000

Data Index: 1956446 (The Pile)

Max Activating Token Index: 699

Text #19

Max Range: 0.6239. Min Range: -0.6239

Max Act: 0.5017. Min Act: -0.0000

Data Index: 292794 (The Pile)

Max Activating Token Index: 989