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

Dataset: The Pile

Neuron 3349 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6158. Min Range: -1.6158

Max Act: 1.6158. Min Act: -0.0000

Data Index: 398272 (The Pile)

Max Activating Token Index: 227

Text #1

Max Range: 1.6158. Min Range: -1.6158

Max Act: 1.2920. Min Act: -0.0000

Data Index: 1601521 (The Pile)

Max Activating Token Index: 199

Text #2

Max Range: 1.6158. Min Range: -1.6158

Max Act: 1.3266. Min Act: -0.0000

Data Index: 1905275 (The Pile)

Max Activating Token Index: 595

Text #3

Max Range: 1.6158. Min Range: -1.6158

Max Act: 1.4045. Min Act: -0.0000

Data Index: 1244564 (The Pile)

Max Activating Token Index: 671

Text #4

Max Range: 1.6158. Min Range: -1.6158

Max Act: 1.3056. Min Act: -0.0000

Data Index: 309630 (The Pile)

Max Activating Token Index: 592

Text #5

Max Range: 1.6158. Min Range: -1.6158

Max Act: 1.2630. Min Act: -0.0000

Data Index: 1264968 (The Pile)

Max Activating Token Index: 706

Text #6

Max Range: 1.6158. Min Range: -1.6158

Max Act: 1.2288. Min Act: -0.0000

Data Index: 1152634 (The Pile)

Max Activating Token Index: 334

Text #7

Max Range: 1.6158. Min Range: -1.6158

Max Act: 1.2768. Min Act: -0.0000

Data Index: 992103 (The Pile)

Max Activating Token Index: 832

Text #8

Max Range: 1.6158. Min Range: -1.6158

Max Act: 1.1966. Min Act: 0.0001

Data Index: 339557 (The Pile)

Max Activating Token Index: 175

Text #9

Max Range: 1.6158. Min Range: -1.6158

Max Act: 1.1559. Min Act: -0.0000

Data Index: 267050 (The Pile)

Max Activating Token Index: 45

Text #10

Max Range: 1.6158. Min Range: -1.6158

Max Act: 1.1895. Min Act: -0.0000

Data Index: 1562192 (The Pile)

Max Activating Token Index: 789

Text #11

Max Range: 1.6158. Min Range: -1.6158

Max Act: 1.1314. Min Act: -0.0000

Data Index: 1970241 (The Pile)

Max Activating Token Index: 352

Text #12

Max Range: 1.6158. Min Range: -1.6158

Max Act: 1.1042. Min Act: -0.0000

Data Index: 596560 (The Pile)

Max Activating Token Index: 111

Text #13

Max Range: 1.6158. Min Range: -1.6158

Max Act: 1.0278. Min Act: -0.0000

Data Index: 78711 (The Pile)

Max Activating Token Index: 209

Text #14

Max Range: 1.6158. Min Range: -1.6158

Max Act: 1.1401. Min Act: -0.0000

Data Index: 1420673 (The Pile)

Max Activating Token Index: 568

Text #15

Max Range: 1.6158. Min Range: -1.6158

Max Act: 1.0665. Min Act: -0.0000

Data Index: 1597689 (The Pile)

Max Activating Token Index: 140

Text #16

Max Range: 1.6158. Min Range: -1.6158

Max Act: 1.1133. Min Act: -0.0000

Data Index: 1746415 (The Pile)

Max Activating Token Index: 634

Text #17

Max Range: 1.6158. Min Range: -1.6158

Max Act: 1.0209. Min Act: -0.0000

Data Index: 119442 (The Pile)

Max Activating Token Index: 130

Text #18

Max Range: 1.6158. Min Range: -1.6158

Max Act: 0.9775. Min Act: -0.0000

Data Index: 917357 (The Pile)

Max Activating Token Index: 717

Text #19

Max Range: 1.6158. Min Range: -1.6158

Max Act: 1.0017. Min Act: -0.0000

Data Index: 793906 (The Pile)

Max Activating Token Index: 727