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

Dataset: The Pile

Neuron 4217 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: 10.4766. Min Range: -10.4766

Max Act: 10.0713. Min Act: -0.0000

Data Index: 944462 (The Pile)

Max Activating Token Index: 452

Text #1

Max Range: 10.4766. Min Range: -10.4766

Max Act: 10.4766. Min Act: -0.0000

Data Index: 719981 (The Pile)

Max Activating Token Index: 1014

Text #2

Max Range: 10.4766. Min Range: -10.4766

Max Act: 9.5386. Min Act: -0.0000

Data Index: 1302785 (The Pile)

Max Activating Token Index: 456

Text #3

Max Range: 10.4766. Min Range: -10.4766

Max Act: 8.2607. Min Act: -0.0000

Data Index: 76150 (The Pile)

Max Activating Token Index: 220

Text #4

Max Range: 10.4766. Min Range: -10.4766

Max Act: 8.5381. Min Act: -0.0000

Data Index: 579908 (The Pile)

Max Activating Token Index: 996

Text #5

Max Range: 10.4766. Min Range: -10.4766

Max Act: 7.9774. Min Act: -0.0000

Data Index: 1412522 (The Pile)

Max Activating Token Index: 872

Text #6

Max Range: 10.4766. Min Range: -10.4766

Max Act: 7.8576. Min Act: -0.0000

Data Index: 1065443 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 10.4766. Min Range: -10.4766

Max Act: 7.9533. Min Act: -0.0000

Data Index: 1792576 (The Pile)

Max Activating Token Index: 1013

Text #8

Max Range: 10.4766. Min Range: -10.4766

Max Act: 7.8209. Min Act: -0.0000

Data Index: 706998 (The Pile)

Max Activating Token Index: 987

Text #9

Max Range: 10.4766. Min Range: -10.4766

Max Act: 7.5355. Min Act: -0.0000

Data Index: 788712 (The Pile)

Max Activating Token Index: 30

Text #10

Max Range: 10.4766. Min Range: -10.4766

Max Act: 7.2348. Min Act: -0.0000

Data Index: 1123789 (The Pile)

Max Activating Token Index: 647

Text #11

Max Range: 10.4766. Min Range: -10.4766

Max Act: 8.1355. Min Act: -0.0000

Data Index: 207113 (The Pile)

Max Activating Token Index: 486

Text #12

Max Range: 10.4766. Min Range: -10.4766

Max Act: 9.1957. Min Act: -0.0000

Data Index: 1358719 (The Pile)

Max Activating Token Index: 779

Text #13

Max Range: 10.4766. Min Range: -10.4766

Max Act: 7.9636. Min Act: -0.0000

Data Index: 1884737 (The Pile)

Max Activating Token Index: 330

Text #14

Max Range: 10.4766. Min Range: -10.4766

Max Act: 8.0248. Min Act: -0.0000

Data Index: 1529020 (The Pile)

Max Activating Token Index: 491

Text #15

Max Range: 10.4766. Min Range: -10.4766

Max Act: 6.2691. Min Act: -0.0000

Data Index: 1804059 (The Pile)

Max Activating Token Index: 154

Text #16

Max Range: 10.4766. Min Range: -10.4766

Max Act: 6.2995. Min Act: -0.0000

Data Index: 113152 (The Pile)

Max Activating Token Index: 400

Text #17

Max Range: 10.4766. Min Range: -10.4766

Max Act: 7.9154. Min Act: -0.0000

Data Index: 310971 (The Pile)

Max Activating Token Index: 761

Text #18

Max Range: 10.4766. Min Range: -10.4766

Max Act: 6.0836. Min Act: -0.0000

Data Index: 679419 (The Pile)

Max Activating Token Index: 829

Text #19

Max Range: 10.4766. Min Range: -10.4766

Max Act: 6.7732. Min Act: -0.0000

Data Index: 1391150 (The Pile)

Max Activating Token Index: 986