Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1637 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.3107. Min Act: -0.0000

Data Index: 57917 (The Pile)

Max Activating Token Index: 494

Text #1

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2655. Min Act: -0.0000

Data Index: 476043 (The Pile)

Max Activating Token Index: 977

Text #2

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2917. Min Act: -0.0000

Data Index: 1663718 (The Pile)

Max Activating Token Index: 904

Text #3

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2853. Min Act: -0.0000

Data Index: 1180873 (The Pile)

Max Activating Token Index: 769

Text #4

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2401. Min Act: -0.0000

Data Index: 730999 (The Pile)

Max Activating Token Index: 878

Text #5

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2804. Min Act: -0.0000

Data Index: 573571 (The Pile)

Max Activating Token Index: 679

Text #6

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2626. Min Act: -0.0000

Data Index: 386240 (The Pile)

Max Activating Token Index: 668

Text #7

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2992. Min Act: -0.0000

Data Index: 1994101 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2558. Min Act: -0.0000

Data Index: 353599 (The Pile)

Max Activating Token Index: 1006

Text #9

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2698. Min Act: -0.0000

Data Index: 1233545 (The Pile)

Max Activating Token Index: 730

Text #10

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2842. Min Act: -0.0000

Data Index: 1049009 (The Pile)

Max Activating Token Index: 40

Text #11

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2858. Min Act: -0.0000

Data Index: 1184472 (The Pile)

Max Activating Token Index: 627

Text #12

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2739. Min Act: -0.0000

Data Index: 1985885 (The Pile)

Max Activating Token Index: 162

Text #13

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2626. Min Act: -0.0000

Data Index: 1773024 (The Pile)

Max Activating Token Index: 179

Text #14

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2567. Min Act: -0.0000

Data Index: 1488123 (The Pile)

Max Activating Token Index: 940

Text #15

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2516. Min Act: -0.0000

Data Index: 497452 (The Pile)

Max Activating Token Index: 947

Text #16

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2510. Min Act: -0.0000

Data Index: 640839 (The Pile)

Max Activating Token Index: 731

Text #17

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2474. Min Act: -0.0000

Data Index: 718243 (The Pile)

Max Activating Token Index: 885

Text #18

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2471. Min Act: -0.0000

Data Index: 1507002 (The Pile)

Max Activating Token Index: 1000

Text #19

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2334. Min Act: -0.0000

Data Index: 1256278 (The Pile)

Max Activating Token Index: 955