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

Dataset: The Pile

Neuron 3989 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7219. Min Range: -3.7219

Max Act: 3.0905. Min Act: -0.0000

Data Index: 1720135 (The Pile)

Max Activating Token Index: 496

Text #1

Max Range: 3.7219. Min Range: -3.7219

Max Act: 3.7219. Min Act: -0.0000

Data Index: 1924913 (The Pile)

Max Activating Token Index: 109

Text #2

Max Range: 3.7219. Min Range: -3.7219

Max Act: 3.1516. Min Act: -0.0000

Data Index: 1410090 (The Pile)

Max Activating Token Index: 397

Text #3

Max Range: 3.7219. Min Range: -3.7219

Max Act: 3.0493. Min Act: -0.0000

Data Index: 54859 (The Pile)

Max Activating Token Index: 797

Text #4

Max Range: 3.7219. Min Range: -3.7219

Max Act: 2.8548. Min Act: -0.0000

Data Index: 824189 (The Pile)

Max Activating Token Index: 959

Text #5

Max Range: 3.7219. Min Range: -3.7219

Max Act: 2.5264. Min Act: -0.0000

Data Index: 1017020 (The Pile)

Max Activating Token Index: 91

Text #6

Max Range: 3.7219. Min Range: -3.7219

Max Act: 1.9174. Min Act: -0.0000

Data Index: 537838 (The Pile)

Max Activating Token Index: 859

Text #7

Max Range: 3.7219. Min Range: -3.7219

Max Act: 2.6615. Min Act: -0.0000

Data Index: 475534 (The Pile)

Max Activating Token Index: 362

Text #8

Max Range: 3.7219. Min Range: -3.7219

Max Act: 2.2310. Min Act: -0.0000

Data Index: 1201245 (The Pile)

Max Activating Token Index: 312

Text #9

Max Range: 3.7219. Min Range: -3.7219

Max Act: 2.3525. Min Act: -0.0000

Data Index: 905514 (The Pile)

Max Activating Token Index: 725

Text #10

Max Range: 3.7219. Min Range: -3.7219

Max Act: 2.0804. Min Act: -0.0000

Data Index: 240612 (The Pile)

Max Activating Token Index: 403

Text #11

Max Range: 3.7219. Min Range: -3.7219

Max Act: 2.0668. Min Act: 0.0000

Data Index: 1761913 (The Pile)

Max Activating Token Index: 674

Text #12

Max Range: 3.7219. Min Range: -3.7219

Max Act: 1.9235. Min Act: -0.0000

Data Index: 1147831 (The Pile)

Max Activating Token Index: 606

Text #13

Max Range: 3.7219. Min Range: -3.7219

Max Act: 1.9409. Min Act: -0.0000

Data Index: 1116872 (The Pile)

Max Activating Token Index: 411

Text #14

Max Range: 3.7219. Min Range: -3.7219

Max Act: 2.2978. Min Act: -0.0000

Data Index: 177429 (The Pile)

Max Activating Token Index: 996

Text #15

Max Range: 3.7219. Min Range: -3.7219

Max Act: 1.9088. Min Act: -0.0000

Data Index: 1862905 (The Pile)

Max Activating Token Index: 837

Text #16

Max Range: 3.7219. Min Range: -3.7219

Max Act: 1.9004. Min Act: -0.0000

Data Index: 1796768 (The Pile)

Max Activating Token Index: 349

Text #17

Max Range: 3.7219. Min Range: -3.7219

Max Act: 1.8551. Min Act: -0.0000

Data Index: 1340797 (The Pile)

Max Activating Token Index: 1006

Text #18

Max Range: 3.7219. Min Range: -3.7219

Max Act: 1.8448. Min Act: 0.0000

Data Index: 1998208 (The Pile)

Max Activating Token Index: 833

Text #19

Max Range: 3.7219. Min Range: -3.7219

Max Act: 1.9068. Min Act: -0.0000

Data Index: 1260278 (The Pile)

Max Activating Token Index: 603