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

Dataset: The Pile

Neuron 1732 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: 0.3981. Min Range: -0.3981

Max Act: 0.3981. Min Act: -0.0000

Data Index: 1308013 (The Pile)

Max Activating Token Index: 817

Text #1

Max Range: 0.3981. Min Range: -0.3981

Max Act: 0.3470. Min Act: -0.0000

Data Index: 972773 (The Pile)

Max Activating Token Index: 425

Text #2

Max Range: 0.3981. Min Range: -0.3981

Max Act: 0.3567. Min Act: -0.0000

Data Index: 1161960 (The Pile)

Max Activating Token Index: 776

Text #3

Max Range: 0.3981. Min Range: -0.3981

Max Act: 0.3460. Min Act: -0.0000

Data Index: 736982 (The Pile)

Max Activating Token Index: 835

Text #4

Max Range: 0.3981. Min Range: -0.3981

Max Act: 0.3335. Min Act: -0.0000

Data Index: 1783489 (The Pile)

Max Activating Token Index: 123

Text #5

Max Range: 0.3981. Min Range: -0.3981

Max Act: 0.3112. Min Act: -0.0000

Data Index: 998951 (The Pile)

Max Activating Token Index: 924

Text #6

Max Range: 0.3981. Min Range: -0.3981

Max Act: 0.3313. Min Act: -0.0000

Data Index: 383226 (The Pile)

Max Activating Token Index: 984

Text #7

Max Range: 0.3981. Min Range: -0.3981

Max Act: 0.2963. Min Act: -0.0000

Data Index: 1881703 (The Pile)

Max Activating Token Index: 772

Text #8

Max Range: 0.3981. Min Range: -0.3981

Max Act: 0.3236. Min Act: -0.0000

Data Index: 1187621 (The Pile)

Max Activating Token Index: 686

Text #9

Max Range: 0.3981. Min Range: -0.3981

Max Act: 0.2962. Min Act: -0.0000

Data Index: 214781 (The Pile)

Max Activating Token Index: 508

Text #10

Max Range: 0.3981. Min Range: -0.3981

Max Act: 0.2944. Min Act: -0.0000

Data Index: 246668 (The Pile)

Max Activating Token Index: 686

Text #11

Max Range: 0.3981. Min Range: -0.3981

Max Act: 0.2918. Min Act: -0.0000

Data Index: 1883340 (The Pile)

Max Activating Token Index: 629

Text #12

Max Range: 0.3981. Min Range: -0.3981

Max Act: 0.2709. Min Act: -0.0000

Data Index: 1872038 (The Pile)

Max Activating Token Index: 804

Text #13

Max Range: 0.3981. Min Range: -0.3981

Max Act: 0.2786. Min Act: -0.0000

Data Index: 1365737 (The Pile)

Max Activating Token Index: 119

Text #14

Max Range: 0.3981. Min Range: -0.3981

Max Act: 0.2796. Min Act: -0.0000

Data Index: 1084057 (The Pile)

Max Activating Token Index: 972

Text #15

Max Range: 0.3981. Min Range: -0.3981

Max Act: 0.2807. Min Act: -0.0000

Data Index: 909683 (The Pile)

Max Activating Token Index: 754

Text #16

Max Range: 0.3981. Min Range: -0.3981

Max Act: 0.2783. Min Act: -0.0000

Data Index: 747207 (The Pile)

Max Activating Token Index: 120

Text #17

Max Range: 0.3981. Min Range: -0.3981

Max Act: 0.2595. Min Act: -0.0000

Data Index: 601892 (The Pile)

Max Activating Token Index: 807

Text #18

Max Range: 0.3981. Min Range: -0.3981

Max Act: 0.2761. Min Act: -0.0000

Data Index: 328215 (The Pile)

Max Activating Token Index: 518

Text #19

Max Range: 0.3981. Min Range: -0.3981

Max Act: 0.2756. Min Act: -0.0000

Data Index: 506621 (The Pile)

Max Activating Token Index: 477