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

Dataset: The Pile

Neuron 2346 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6165. Min Range: -1.6165

Max Act: 1.6165. Min Act: -0.0000

Data Index: 1303671 (The Pile)

Max Activating Token Index: 755

Text #1

Max Range: 1.6165. Min Range: -1.6165

Max Act: 1.5565. Min Act: -0.0000

Data Index: 604757 (The Pile)

Max Activating Token Index: 260

Text #2

Max Range: 1.6165. Min Range: -1.6165

Max Act: 1.1811. Min Act: -0.0000

Data Index: 767187 (The Pile)

Max Activating Token Index: 777

Text #3

Max Range: 1.6165. Min Range: -1.6165

Max Act: 1.3080. Min Act: -0.0000

Data Index: 16928 (The Pile)

Max Activating Token Index: 503

Text #4

Max Range: 1.6165. Min Range: -1.6165

Max Act: 1.2322. Min Act: -0.0000

Data Index: 116577 (The Pile)

Max Activating Token Index: 667

Text #5

Max Range: 1.6165. Min Range: -1.6165

Max Act: 1.1756. Min Act: -0.0000

Data Index: 1546086 (The Pile)

Max Activating Token Index: 547

Text #6

Max Range: 1.6165. Min Range: -1.6165

Max Act: 1.1815. Min Act: -0.0000

Data Index: 1823952 (The Pile)

Max Activating Token Index: 833

Text #7

Max Range: 1.6165. Min Range: -1.6165

Max Act: 1.1232. Min Act: -0.0000

Data Index: 1441478 (The Pile)

Max Activating Token Index: 483

Text #8

Max Range: 1.6165. Min Range: -1.6165

Max Act: 1.0507. Min Act: -0.0000

Data Index: 1988786 (The Pile)

Max Activating Token Index: 474

Text #9

Max Range: 1.6165. Min Range: -1.6165

Max Act: 1.1144. Min Act: -0.0000

Data Index: 859510 (The Pile)

Max Activating Token Index: 810

Text #10

Max Range: 1.6165. Min Range: -1.6165

Max Act: 0.8811. Min Act: -0.0000

Data Index: 677195 (The Pile)

Max Activating Token Index: 836

Text #11

Max Range: 1.6165. Min Range: -1.6165

Max Act: 1.0473. Min Act: -0.0000

Data Index: 1800162 (The Pile)

Max Activating Token Index: 525

Text #12

Max Range: 1.6165. Min Range: -1.6165

Max Act: 0.9436. Min Act: -0.0000

Data Index: 27701 (The Pile)

Max Activating Token Index: 866

Text #13

Max Range: 1.6165. Min Range: -1.6165

Max Act: 0.8980. Min Act: -0.0000

Data Index: 1678670 (The Pile)

Max Activating Token Index: 939

Text #14

Max Range: 1.6165. Min Range: -1.6165

Max Act: 0.8978. Min Act: -0.0000

Data Index: 962651 (The Pile)

Max Activating Token Index: 586

Text #15

Max Range: 1.6165. Min Range: -1.6165

Max Act: 0.8407. Min Act: -0.0000

Data Index: 468384 (The Pile)

Max Activating Token Index: 608

Text #16

Max Range: 1.6165. Min Range: -1.6165

Max Act: 0.7828. Min Act: -0.0000

Data Index: 1634211 (The Pile)

Max Activating Token Index: 697

Text #17

Max Range: 1.6165. Min Range: -1.6165

Max Act: 0.7848. Min Act: -0.0000

Data Index: 724206 (The Pile)

Max Activating Token Index: 987

Text #18

Max Range: 1.6165. Min Range: -1.6165

Max Act: 0.8736. Min Act: -0.0000

Data Index: 662559 (The Pile)

Max Activating Token Index: 999

Text #19

Max Range: 1.6165. Min Range: -1.6165

Max Act: 0.8154. Min Act: -0.0000

Data Index: 1581714 (The Pile)

Max Activating Token Index: 840