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

Dataset: The Pile

Neuron 1119 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: 1.3199. Min Range: -1.3199

Max Act: 1.3199. Min Act: -0.0000

Data Index: 834879 (The Pile)

Max Activating Token Index: 733

Text #1

Max Range: 1.3199. Min Range: -1.3199

Max Act: 0.9060. Min Act: -0.0000

Data Index: 1652922 (The Pile)

Max Activating Token Index: 151

Text #2

Max Range: 1.3199. Min Range: -1.3199

Max Act: 0.8711. Min Act: -0.0000

Data Index: 1104273 (The Pile)

Max Activating Token Index: 145

Text #3

Max Range: 1.3199. Min Range: -1.3199

Max Act: 0.8582. Min Act: -0.0000

Data Index: 795683 (The Pile)

Max Activating Token Index: 333

Text #4

Max Range: 1.3199. Min Range: -1.3199

Max Act: 0.7188. Min Act: -0.0000

Data Index: 1743954 (The Pile)

Max Activating Token Index: 977

Text #5

Max Range: 1.3199. Min Range: -1.3199

Max Act: 0.7464. Min Act: -0.0000

Data Index: 1386155 (The Pile)

Max Activating Token Index: 566

Text #6

Max Range: 1.3199. Min Range: -1.3199

Max Act: 0.6596. Min Act: -0.0000

Data Index: 761604 (The Pile)

Max Activating Token Index: 604

Text #7

Max Range: 1.3199. Min Range: -1.3199

Max Act: 0.6046. Min Act: -0.0000

Data Index: 1964058 (The Pile)

Max Activating Token Index: 1017

Text #8

Max Range: 1.3199. Min Range: -1.3199

Max Act: 0.5318. Min Act: -0.0000

Data Index: 594216 (The Pile)

Max Activating Token Index: 892

Text #9

Max Range: 1.3199. Min Range: -1.3199

Max Act: 0.6875. Min Act: -0.0000

Data Index: 1177328 (The Pile)

Max Activating Token Index: 548

Text #10

Max Range: 1.3199. Min Range: -1.3199

Max Act: 0.6520. Min Act: -0.0000

Data Index: 1093870 (The Pile)

Max Activating Token Index: 107

Text #11

Max Range: 1.3199. Min Range: -1.3199

Max Act: 0.5275. Min Act: -0.0000

Data Index: 1085228 (The Pile)

Max Activating Token Index: 1003

Text #12

Max Range: 1.3199. Min Range: -1.3199

Max Act: 0.5040. Min Act: -0.0000

Data Index: 1273651 (The Pile)

Max Activating Token Index: 847

Text #13

Max Range: 1.3199. Min Range: -1.3199

Max Act: 0.6360. Min Act: -0.0000

Data Index: 1978286 (The Pile)

Max Activating Token Index: 745

Text #14

Max Range: 1.3199. Min Range: -1.3199

Max Act: 0.5421. Min Act: -0.0000

Data Index: 871338 (The Pile)

Max Activating Token Index: 182

Text #15

Max Range: 1.3199. Min Range: -1.3199

Max Act: 0.5673. Min Act: -0.0000

Data Index: 790935 (The Pile)

Max Activating Token Index: 262

Text #16

Max Range: 1.3199. Min Range: -1.3199

Max Act: 0.5590. Min Act: -0.0000

Data Index: 1915383 (The Pile)

Max Activating Token Index: 961

Text #17

Max Range: 1.3199. Min Range: -1.3199

Max Act: 0.5726. Min Act: -0.0000

Data Index: 1024575 (The Pile)

Max Activating Token Index: 294

Text #18

Max Range: 1.3199. Min Range: -1.3199

Max Act: 0.6458. Min Act: -0.0000

Data Index: 1892513 (The Pile)

Max Activating Token Index: 298

Text #19

Max Range: 1.3199. Min Range: -1.3199

Max Act: 0.5896. Min Act: -0.0000

Data Index: 1227258 (The Pile)

Max Activating Token Index: 549