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

Dataset: The Pile

Neuron 5072 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: 0.6866. Min Range: -0.6866

Max Act: 0.6495. Min Act: -0.0000

Data Index: 354135 (The Pile)

Max Activating Token Index: 296

Text #1

Max Range: 0.6866. Min Range: -0.6866

Max Act: 0.6681. Min Act: -0.0000

Data Index: 281451 (The Pile)

Max Activating Token Index: 195

Text #2

Max Range: 0.6866. Min Range: -0.6866

Max Act: 0.6866. Min Act: -0.0000

Data Index: 1196535 (The Pile)

Max Activating Token Index: 491

Text #3

Max Range: 0.6866. Min Range: -0.6866

Max Act: 0.6559. Min Act: -0.0000

Data Index: 1963795 (The Pile)

Max Activating Token Index: 438

Text #4

Max Range: 0.6866. Min Range: -0.6866

Max Act: 0.6443. Min Act: -0.0000

Data Index: 383103 (The Pile)

Max Activating Token Index: 664

Text #5

Max Range: 0.6866. Min Range: -0.6866

Max Act: 0.6191. Min Act: -0.0000

Data Index: 1523385 (The Pile)

Max Activating Token Index: 481

Text #6

Max Range: 0.6866. Min Range: -0.6866

Max Act: 0.6458. Min Act: -0.0000

Data Index: 1365103 (The Pile)

Max Activating Token Index: 822

Text #7

Max Range: 0.6866. Min Range: -0.6866

Max Act: 0.6239. Min Act: -0.0000

Data Index: 784584 (The Pile)

Max Activating Token Index: 240

Text #8

Max Range: 0.6866. Min Range: -0.6866

Max Act: 0.5843. Min Act: -0.0000

Data Index: 313331 (The Pile)

Max Activating Token Index: 598

Text #9

Max Range: 0.6866. Min Range: -0.6866

Max Act: 0.6375. Min Act: -0.0000

Data Index: 99450 (The Pile)

Max Activating Token Index: 195

Text #10

Max Range: 0.6866. Min Range: -0.6866

Max Act: 0.6168. Min Act: -0.0000

Data Index: 1776016 (The Pile)

Max Activating Token Index: 684

Text #11

Max Range: 0.6866. Min Range: -0.6866

Max Act: 0.6423. Min Act: -0.0000

Data Index: 992995 (The Pile)

Max Activating Token Index: 985

Text #12

Max Range: 0.6866. Min Range: -0.6866

Max Act: 0.5747. Min Act: -0.0000

Data Index: 578161 (The Pile)

Max Activating Token Index: 628

Text #13

Max Range: 0.6866. Min Range: -0.6866

Max Act: 0.5864. Min Act: -0.0000

Data Index: 921132 (The Pile)

Max Activating Token Index: 269

Text #14

Max Range: 0.6866. Min Range: -0.6866

Max Act: 0.5778. Min Act: -0.0000

Data Index: 931827 (The Pile)

Max Activating Token Index: 814

Text #15

Max Range: 0.6866. Min Range: -0.6866

Max Act: 0.5906. Min Act: -0.0000

Data Index: 143509 (The Pile)

Max Activating Token Index: 218

Text #16

Max Range: 0.6866. Min Range: -0.6866

Max Act: 0.6069. Min Act: -0.0000

Data Index: 1150300 (The Pile)

Max Activating Token Index: 271

Text #17

Max Range: 0.6866. Min Range: -0.6866

Max Act: 0.5848. Min Act: -0.0000

Data Index: 1492894 (The Pile)

Max Activating Token Index: 469

Text #18

Max Range: 0.6866. Min Range: -0.6866

Max Act: 0.6064. Min Act: -0.0000

Data Index: 1858821 (The Pile)

Max Activating Token Index: 388

Text #19

Max Range: 0.6866. Min Range: -0.6866

Max Act: 0.5870. Min Act: -0.0000

Data Index: 335056 (The Pile)

Max Activating Token Index: 795