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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2763 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0680. Min Act: -0.0002

Data Index: 340474 (C4 (Web Text))

Max Activating Token Index: 738

Text #1

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0813. Min Act: -0.0002

Data Index: 232108 (C4 (Web Text))

Max Activating Token Index: 87

Text #2

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0759. Min Act: -0.0002

Data Index: 1047529 (C4 (Web Text))

Max Activating Token Index: 747

Text #3

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0646. Min Act: -0.0002

Data Index: 594238 (C4 (Web Text))

Max Activating Token Index: 195

Text #4

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0685. Min Act: -0.0002

Data Index: 446347 (C4 (Web Text))

Max Activating Token Index: 721

Text #5

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0570. Min Act: -0.0002

Data Index: 207796 (C4 (Web Text))

Max Activating Token Index: 377

Text #6

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0679. Min Act: -0.0002

Data Index: 940021 (C4 (Web Text))

Max Activating Token Index: 1011

Text #7

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0682. Min Act: -0.0002

Data Index: 871987 (C4 (Web Text))

Max Activating Token Index: 587

Text #8

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0577. Min Act: -0.0002

Data Index: 607126 (C4 (Web Text))

Max Activating Token Index: 247

Text #9

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0643. Min Act: -0.0002

Data Index: 249473 (C4 (Web Text))

Max Activating Token Index: 433

Text #10

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0635. Min Act: -0.0002

Data Index: 554188 (C4 (Web Text))

Max Activating Token Index: 870

Text #11

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0679. Min Act: -0.0002

Data Index: 1027760 (C4 (Web Text))

Max Activating Token Index: 210

Text #12

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0538. Min Act: -0.0002

Data Index: 1102512 (C4 (Web Text))

Max Activating Token Index: 311

Text #13

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0594. Min Act: -0.0002

Data Index: 1344636 (C4 (Web Text))

Max Activating Token Index: 612

Text #14

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0620. Min Act: -0.0002

Data Index: 504061 (C4 (Web Text))

Max Activating Token Index: 974

Text #15

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0511. Min Act: -0.0002

Data Index: 710432 (C4 (Web Text))

Max Activating Token Index: 378

Text #16

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0620. Min Act: -0.0002

Data Index: 641052 (C4 (Web Text))

Max Activating Token Index: 788

Text #17

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0506. Min Act: -0.0002

Data Index: 173678 (C4 (Web Text))

Max Activating Token Index: 573

Text #18

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0585. Min Act: -0.0002

Data Index: 332520 (C4 (Web Text))

Max Activating Token Index: 458

Text #19

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0654. Min Act: -0.0002

Data Index: 14748 (C4 (Web Text))

Max Activating Token Index: 405