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

Dataset: The Pile

Neuron 1899 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: 1.5548. Min Range: -1.5548

Max Act: 1.5548. Min Act: -0.0000

Data Index: 705484 (The Pile)

Max Activating Token Index: 129

Text #1

Max Range: 1.5548. Min Range: -1.5548

Max Act: 1.3267. Min Act: -0.0000

Data Index: 278274 (The Pile)

Max Activating Token Index: 330

Text #2

Max Range: 1.5548. Min Range: -1.5548

Max Act: 1.2611. Min Act: -0.0000

Data Index: 1889854 (The Pile)

Max Activating Token Index: 826

Text #3

Max Range: 1.5548. Min Range: -1.5548

Max Act: 1.1664. Min Act: -0.0000

Data Index: 1033097 (The Pile)

Max Activating Token Index: 76

Text #4

Max Range: 1.5548. Min Range: -1.5548

Max Act: 1.1349. Min Act: -0.0000

Data Index: 972700 (The Pile)

Max Activating Token Index: 11

Text #5

Max Range: 1.5548. Min Range: -1.5548

Max Act: 1.1151. Min Act: -0.0000

Data Index: 624386 (The Pile)

Max Activating Token Index: 144

Text #6

Max Range: 1.5548. Min Range: -1.5548

Max Act: 1.0593. Min Act: -0.0000

Data Index: 858680 (The Pile)

Max Activating Token Index: 131

Text #7

Max Range: 1.5548. Min Range: -1.5548

Max Act: 0.9382. Min Act: -0.0000

Data Index: 1176047 (The Pile)

Max Activating Token Index: 8

Text #8

Max Range: 1.5548. Min Range: -1.5548

Max Act: 1.0741. Min Act: -0.0000

Data Index: 382978 (The Pile)

Max Activating Token Index: 250

Text #9

Max Range: 1.5548. Min Range: -1.5548

Max Act: 1.0655. Min Act: -0.0000

Data Index: 474602 (The Pile)

Max Activating Token Index: 176

Text #10

Max Range: 1.5548. Min Range: -1.5548

Max Act: 0.9610. Min Act: -0.0000

Data Index: 718866 (The Pile)

Max Activating Token Index: 520

Text #11

Max Range: 1.5548. Min Range: -1.5548

Max Act: 0.9301. Min Act: -0.0000

Data Index: 687183 (The Pile)

Max Activating Token Index: 673

Text #12

Max Range: 1.5548. Min Range: -1.5548

Max Act: 1.0788. Min Act: -0.0000

Data Index: 1735417 (The Pile)

Max Activating Token Index: 679

Text #13

Max Range: 1.5548. Min Range: -1.5548

Max Act: 0.9656. Min Act: -0.0000

Data Index: 1042928 (The Pile)

Max Activating Token Index: 963

Text #14

Max Range: 1.5548. Min Range: -1.5548

Max Act: 1.1087. Min Act: -0.0000

Data Index: 1985421 (The Pile)

Max Activating Token Index: 78

Text #15

Max Range: 1.5548. Min Range: -1.5548

Max Act: 0.9654. Min Act: -0.0000

Data Index: 1994350 (The Pile)

Max Activating Token Index: 121

Text #16

Max Range: 1.5548. Min Range: -1.5548

Max Act: 0.9798. Min Act: -0.0000

Data Index: 1021509 (The Pile)

Max Activating Token Index: 41

Text #17

Max Range: 1.5548. Min Range: -1.5548

Max Act: 1.0324. Min Act: -0.0000

Data Index: 829422 (The Pile)

Max Activating Token Index: 485

Text #18

Max Range: 1.5548. Min Range: -1.5548

Max Act: 0.9670. Min Act: -0.0000

Data Index: 380310 (The Pile)

Max Activating Token Index: 236

Text #19

Max Range: 1.5548. Min Range: -1.5548

Max Act: 0.9628. Min Act: -0.0000

Data Index: 1643963 (The Pile)

Max Activating Token Index: 754