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

Dataset: The Pile

Neuron 2670 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4815. Min Range: -0.4815

Max Act: 0.4815. Min Act: -0.0000

Data Index: 1596536 (The Pile)

Max Activating Token Index: 1017

Text #1

Max Range: 0.4815. Min Range: -0.4815

Max Act: 0.3849. Min Act: -0.0000

Data Index: 1094163 (The Pile)

Max Activating Token Index: 856

Text #2

Max Range: 0.4815. Min Range: -0.4815

Max Act: 0.3976. Min Act: -0.0000

Data Index: 1769754 (The Pile)

Max Activating Token Index: 416

Text #3

Max Range: 0.4815. Min Range: -0.4815

Max Act: 0.3540. Min Act: -0.0000

Data Index: 1605944 (The Pile)

Max Activating Token Index: 959

Text #4

Max Range: 0.4815. Min Range: -0.4815

Max Act: 0.3645. Min Act: -0.0000

Data Index: 804338 (The Pile)

Max Activating Token Index: 517

Text #5

Max Range: 0.4815. Min Range: -0.4815

Max Act: 0.3644. Min Act: -0.0000

Data Index: 287503 (The Pile)

Max Activating Token Index: 84

Text #6

Max Range: 0.4815. Min Range: -0.4815

Max Act: 0.3676. Min Act: -0.0000

Data Index: 398712 (The Pile)

Max Activating Token Index: 664

Text #7

Max Range: 0.4815. Min Range: -0.4815

Max Act: 0.4020. Min Act: -0.0000

Data Index: 526835 (The Pile)

Max Activating Token Index: 72

Text #8

Max Range: 0.4815. Min Range: -0.4815

Max Act: 0.3287. Min Act: -0.0000

Data Index: 228288 (The Pile)

Max Activating Token Index: 272

Text #9

Max Range: 0.4815. Min Range: -0.4815

Max Act: 0.3177. Min Act: -0.0000

Data Index: 1729167 (The Pile)

Max Activating Token Index: 197

Text #10

Max Range: 0.4815. Min Range: -0.4815

Max Act: 0.3059. Min Act: -0.0000

Data Index: 881921 (The Pile)

Max Activating Token Index: 663

Text #11

Max Range: 0.4815. Min Range: -0.4815

Max Act: 0.3186. Min Act: -0.0000

Data Index: 1183833 (The Pile)

Max Activating Token Index: 312

Text #12

Max Range: 0.4815. Min Range: -0.4815

Max Act: 0.3228. Min Act: -0.0000

Data Index: 493173 (The Pile)

Max Activating Token Index: 998

Text #13

Max Range: 0.4815. Min Range: -0.4815

Max Act: 0.2924. Min Act: -0.0000

Data Index: 1435653 (The Pile)

Max Activating Token Index: 145

Text #14

Max Range: 0.4815. Min Range: -0.4815

Max Act: 0.3201. Min Act: -0.0000

Data Index: 48341 (The Pile)

Max Activating Token Index: 27

Text #15

Max Range: 0.4815. Min Range: -0.4815

Max Act: 0.2793. Min Act: -0.0000

Data Index: 1170722 (The Pile)

Max Activating Token Index: 599

Text #16

Max Range: 0.4815. Min Range: -0.4815

Max Act: 0.2787. Min Act: -0.0000

Data Index: 1915695 (The Pile)

Max Activating Token Index: 493

Text #17

Max Range: 0.4815. Min Range: -0.4815

Max Act: 0.2842. Min Act: -0.0000

Data Index: 1754612 (The Pile)

Max Activating Token Index: 937

Text #18

Max Range: 0.4815. Min Range: -0.4815

Max Act: 0.2955. Min Act: -0.0000

Data Index: 419613 (The Pile)

Max Activating Token Index: 554

Text #19

Max Range: 0.4815. Min Range: -0.4815

Max Act: 0.2942. Min Act: -0.0000

Data Index: 1693978 (The Pile)

Max Activating Token Index: 646