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

Dataset: The Pile

Neuron 4694 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: 3.4175. Min Range: -3.4175

Max Act: 3.3980. Min Act: -0.0000

Data Index: 416876 (The Pile)

Max Activating Token Index: 863

Text #1

Max Range: 3.4175. Min Range: -3.4175

Max Act: 3.3959. Min Act: -0.0000

Data Index: 205012 (The Pile)

Max Activating Token Index: 964

Text #2

Max Range: 3.4175. Min Range: -3.4175

Max Act: 3.4175. Min Act: -0.0000

Data Index: 1247112 (The Pile)

Max Activating Token Index: 1002

Text #3

Max Range: 3.4175. Min Range: -3.4175

Max Act: 3.2676. Min Act: -0.0000

Data Index: 352983 (The Pile)

Max Activating Token Index: 742

Text #4

Max Range: 3.4175. Min Range: -3.4175

Max Act: 3.2748. Min Act: -0.0000

Data Index: 1187322 (The Pile)

Max Activating Token Index: 52

Text #5

Max Range: 3.4175. Min Range: -3.4175

Max Act: 3.2736. Min Act: -0.0000

Data Index: 923815 (The Pile)

Max Activating Token Index: 973

Text #6

Max Range: 3.4175. Min Range: -3.4175

Max Act: 3.2541. Min Act: -0.0000

Data Index: 142166 (The Pile)

Max Activating Token Index: 459

Text #7

Max Range: 3.4175. Min Range: -3.4175

Max Act: 2.9576. Min Act: -0.0000

Data Index: 502038 (The Pile)

Max Activating Token Index: 711

Text #8

Max Range: 3.4175. Min Range: -3.4175

Max Act: 3.1421. Min Act: -0.0000

Data Index: 1471775 (The Pile)

Max Activating Token Index: 574

Text #9

Max Range: 3.4175. Min Range: -3.4175

Max Act: 3.2216. Min Act: -0.0000

Data Index: 940549 (The Pile)

Max Activating Token Index: 109

Text #10

Max Range: 3.4175. Min Range: -3.4175

Max Act: 3.2239. Min Act: -0.0000

Data Index: 1287037 (The Pile)

Max Activating Token Index: 84

Text #11

Max Range: 3.4175. Min Range: -3.4175

Max Act: 2.9880. Min Act: -0.0000

Data Index: 594765 (The Pile)

Max Activating Token Index: 934

Text #12

Max Range: 3.4175. Min Range: -3.4175

Max Act: 3.1884. Min Act: -0.0000

Data Index: 531558 (The Pile)

Max Activating Token Index: 154

Text #13

Max Range: 3.4175. Min Range: -3.4175

Max Act: 2.8280. Min Act: -0.0000

Data Index: 695920 (The Pile)

Max Activating Token Index: 957

Text #14

Max Range: 3.4175. Min Range: -3.4175

Max Act: 3.0947. Min Act: -0.0000

Data Index: 1519742 (The Pile)

Max Activating Token Index: 451

Text #15

Max Range: 3.4175. Min Range: -3.4175

Max Act: 3.0686. Min Act: -0.0000

Data Index: 1195429 (The Pile)

Max Activating Token Index: 559

Text #16

Max Range: 3.4175. Min Range: -3.4175

Max Act: 2.9355. Min Act: -0.0000

Data Index: 271746 (The Pile)

Max Activating Token Index: 976

Text #17

Max Range: 3.4175. Min Range: -3.4175

Max Act: 3.0818. Min Act: -0.0000

Data Index: 572826 (The Pile)

Max Activating Token Index: 389

Text #18

Max Range: 3.4175. Min Range: -3.4175

Max Act: 3.1304. Min Act: -0.0000

Data Index: 1948601 (The Pile)

Max Activating Token Index: 315

Text #19

Max Range: 3.4175. Min Range: -3.4175

Max Act: 2.9794. Min Act: -0.0000

Data Index: 437874 (The Pile)

Max Activating Token Index: 203