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

Dataset: The Pile

Neuron 4830 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: 0.5596. Min Range: -0.5596

Max Act: 0.5596. Min Act: -0.0000

Data Index: 633330 (The Pile)

Max Activating Token Index: 697

Text #1

Max Range: 0.5596. Min Range: -0.5596

Max Act: 0.5364. Min Act: -0.0000

Data Index: 1498124 (The Pile)

Max Activating Token Index: 207

Text #2

Max Range: 0.5596. Min Range: -0.5596

Max Act: 0.5273. Min Act: -0.0000

Data Index: 1112416 (The Pile)

Max Activating Token Index: 788

Text #3

Max Range: 0.5596. Min Range: -0.5596

Max Act: 0.5442. Min Act: -0.0000

Data Index: 25110 (The Pile)

Max Activating Token Index: 533

Text #4

Max Range: 0.5596. Min Range: -0.5596

Max Act: 0.4888. Min Act: -0.0000

Data Index: 1336211 (The Pile)

Max Activating Token Index: 791

Text #5

Max Range: 0.5596. Min Range: -0.5596

Max Act: 0.5141. Min Act: -0.0000

Data Index: 683336 (The Pile)

Max Activating Token Index: 53

Text #6

Max Range: 0.5596. Min Range: -0.5596

Max Act: 0.5156. Min Act: -0.0000

Data Index: 1856970 (The Pile)

Max Activating Token Index: 237

Text #7

Max Range: 0.5596. Min Range: -0.5596

Max Act: 0.4713. Min Act: -0.0000

Data Index: 1693495 (The Pile)

Max Activating Token Index: 884

Text #8

Max Range: 0.5596. Min Range: -0.5596

Max Act: 0.4859. Min Act: -0.0000

Data Index: 465154 (The Pile)

Max Activating Token Index: 351

Text #9

Max Range: 0.5596. Min Range: -0.5596

Max Act: 0.4590. Min Act: -0.0000

Data Index: 179807 (The Pile)

Max Activating Token Index: 415

Text #10

Max Range: 0.5596. Min Range: -0.5596

Max Act: 0.5322. Min Act: -0.0000

Data Index: 1087944 (The Pile)

Max Activating Token Index: 686

Text #11

Max Range: 0.5596. Min Range: -0.5596

Max Act: 0.4970. Min Act: -0.0000

Data Index: 1353647 (The Pile)

Max Activating Token Index: 865

Text #12

Max Range: 0.5596. Min Range: -0.5596

Max Act: 0.5012. Min Act: -0.0000

Data Index: 960833 (The Pile)

Max Activating Token Index: 971

Text #13

Max Range: 0.5596. Min Range: -0.5596

Max Act: 0.4467. Min Act: -0.0000

Data Index: 384087 (The Pile)

Max Activating Token Index: 311

Text #14

Max Range: 0.5596. Min Range: -0.5596

Max Act: 0.4728. Min Act: -0.0000

Data Index: 334995 (The Pile)

Max Activating Token Index: 344

Text #15

Max Range: 0.5596. Min Range: -0.5596

Max Act: 0.4884. Min Act: -0.0000

Data Index: 1805205 (The Pile)

Max Activating Token Index: 679

Text #16

Max Range: 0.5596. Min Range: -0.5596

Max Act: 0.4533. Min Act: -0.0000

Data Index: 943229 (The Pile)

Max Activating Token Index: 762

Text #17

Max Range: 0.5596. Min Range: -0.5596

Max Act: 0.4256. Min Act: -0.0000

Data Index: 26493 (The Pile)

Max Activating Token Index: 1012

Text #18

Max Range: 0.5596. Min Range: -0.5596

Max Act: 0.4499. Min Act: -0.0000

Data Index: 1125274 (The Pile)

Max Activating Token Index: 571

Text #19

Max Range: 0.5596. Min Range: -0.5596

Max Act: 0.4358. Min Act: -0.0000

Data Index: 1792842 (The Pile)

Max Activating Token Index: 142