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

Dataset: The Pile

Neuron 3032 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: 0.9527. Min Range: -0.9527

Max Act: 0.9527. Min Act: -0.0000

Data Index: 1016213 (The Pile)

Max Activating Token Index: 848

Text #1

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.6844. Min Act: -0.0000

Data Index: 1395585 (The Pile)

Max Activating Token Index: 857

Text #2

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.7485. Min Act: -0.0000

Data Index: 1074330 (The Pile)

Max Activating Token Index: 665

Text #3

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.7286. Min Act: -0.0000

Data Index: 1560040 (The Pile)

Max Activating Token Index: 229

Text #4

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.6748. Min Act: -0.0000

Data Index: 722978 (The Pile)

Max Activating Token Index: 787

Text #5

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.6678. Min Act: -0.0000

Data Index: 799606 (The Pile)

Max Activating Token Index: 1015

Text #6

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.6457. Min Act: -0.0000

Data Index: 976936 (The Pile)

Max Activating Token Index: 522

Text #7

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.6868. Min Act: -0.0000

Data Index: 416255 (The Pile)

Max Activating Token Index: 442

Text #8

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.6386. Min Act: -0.0000

Data Index: 387378 (The Pile)

Max Activating Token Index: 610

Text #9

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.6193. Min Act: -0.0000

Data Index: 1041187 (The Pile)

Max Activating Token Index: 62

Text #10

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.6628. Min Act: -0.0000

Data Index: 78421 (The Pile)

Max Activating Token Index: 908

Text #11

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.6249. Min Act: -0.0000

Data Index: 1376859 (The Pile)

Max Activating Token Index: 992

Text #12

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.6186. Min Act: -0.0000

Data Index: 1199083 (The Pile)

Max Activating Token Index: 932

Text #13

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.6510. Min Act: -0.0000

Data Index: 1114900 (The Pile)

Max Activating Token Index: 457

Text #14

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.6733. Min Act: -0.0000

Data Index: 1148315 (The Pile)

Max Activating Token Index: 798

Text #15

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.6359. Min Act: -0.0000

Data Index: 1694903 (The Pile)

Max Activating Token Index: 44

Text #16

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.5986. Min Act: -0.0000

Data Index: 1142068 (The Pile)

Max Activating Token Index: 237

Text #17

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.6128. Min Act: -0.0000

Data Index: 665351 (The Pile)

Max Activating Token Index: 82

Text #18

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.6281. Min Act: -0.0000

Data Index: 1939788 (The Pile)

Max Activating Token Index: 967

Text #19

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.6114. Min Act: -0.0000

Data Index: 147419 (The Pile)

Max Activating Token Index: 335