Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3307 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.5494. Min Range: -0.5494

Max Act: 0.5494. Min Act: -0.0000

Data Index: 67246 (The Pile)

Max Activating Token Index: 19

Text #1

Max Range: 0.5494. Min Range: -0.5494

Max Act: 0.5237. Min Act: -0.0000

Data Index: 1432941 (The Pile)

Max Activating Token Index: 580

Text #2

Max Range: 0.5494. Min Range: -0.5494

Max Act: 0.4884. Min Act: -0.0000

Data Index: 153810 (The Pile)

Max Activating Token Index: 551

Text #3

Max Range: 0.5494. Min Range: -0.5494

Max Act: 0.4754. Min Act: -0.0000

Data Index: 1235533 (The Pile)

Max Activating Token Index: 520

Text #4

Max Range: 0.5494. Min Range: -0.5494

Max Act: 0.5139. Min Act: -0.0000

Data Index: 348744 (The Pile)

Max Activating Token Index: 331

Text #5

Max Range: 0.5494. Min Range: -0.5494

Max Act: 0.4941. Min Act: -0.0000

Data Index: 1037861 (The Pile)

Max Activating Token Index: 43

Text #6

Max Range: 0.5494. Min Range: -0.5494

Max Act: 0.5278. Min Act: -0.0000

Data Index: 934637 (The Pile)

Max Activating Token Index: 430

Text #7

Max Range: 0.5494. Min Range: -0.5494

Max Act: 0.4842. Min Act: -0.0000

Data Index: 788165 (The Pile)

Max Activating Token Index: 169

Text #8

Max Range: 0.5494. Min Range: -0.5494

Max Act: 0.4804. Min Act: -0.0000

Data Index: 1391937 (The Pile)

Max Activating Token Index: 316

Text #9

Max Range: 0.5494. Min Range: -0.5494

Max Act: 0.4218. Min Act: -0.0000

Data Index: 651 (The Pile)

Max Activating Token Index: 887

Text #10

Max Range: 0.5494. Min Range: -0.5494

Max Act: 0.4451. Min Act: -0.0000

Data Index: 1211525 (The Pile)

Max Activating Token Index: 952

Text #11

Max Range: 0.5494. Min Range: -0.5494

Max Act: 0.4268. Min Act: -0.0000

Data Index: 929870 (The Pile)

Max Activating Token Index: 853

Text #12

Max Range: 0.5494. Min Range: -0.5494

Max Act: 0.4466. Min Act: -0.0000

Data Index: 693744 (The Pile)

Max Activating Token Index: 220

Text #13

Max Range: 0.5494. Min Range: -0.5494

Max Act: 0.4616. Min Act: -0.0000

Data Index: 1367071 (The Pile)

Max Activating Token Index: 155

Text #14

Max Range: 0.5494. Min Range: -0.5494

Max Act: 0.4168. Min Act: -0.0000

Data Index: 1000176 (The Pile)

Max Activating Token Index: 638

Text #15

Max Range: 0.5494. Min Range: -0.5494

Max Act: 0.4077. Min Act: -0.0000

Data Index: 680676 (The Pile)

Max Activating Token Index: 394

Text #16

Max Range: 0.5494. Min Range: -0.5494

Max Act: 0.4009. Min Act: -0.0000

Data Index: 126122 (The Pile)

Max Activating Token Index: 109

Text #17

Max Range: 0.5494. Min Range: -0.5494

Max Act: 0.4322. Min Act: -0.0000

Data Index: 1387102 (The Pile)

Max Activating Token Index: 364

Text #18

Max Range: 0.5494. Min Range: -0.5494

Max Act: 0.4280. Min Act: -0.0000

Data Index: 225997 (The Pile)

Max Activating Token Index: 723

Text #19

Max Range: 0.5494. Min Range: -0.5494

Max Act: 0.4270. Min Act: -0.0000

Data Index: 1684457 (The Pile)

Max Activating Token Index: 271