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

Dataset: The Pile

Neuron 3138 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7736. Min Range: -3.7736

Max Act: 3.4226. Min Act: -0.0000

Data Index: 1751506 (The Pile)

Max Activating Token Index: 529

Text #1

Max Range: 3.7736. Min Range: -3.7736

Max Act: 3.2657. Min Act: -0.0000

Data Index: 1064029 (The Pile)

Max Activating Token Index: 727

Text #2

Max Range: 3.7736. Min Range: -3.7736

Max Act: 3.4785. Min Act: -0.0000

Data Index: 197931 (The Pile)

Max Activating Token Index: 473

Text #3

Max Range: 3.7736. Min Range: -3.7736

Max Act: 3.7736. Min Act: -0.0000

Data Index: 1890079 (The Pile)

Max Activating Token Index: 584

Text #4

Max Range: 3.7736. Min Range: -3.7736

Max Act: 3.4494. Min Act: -0.0000

Data Index: 1658256 (The Pile)

Max Activating Token Index: 657

Text #5

Max Range: 3.7736. Min Range: -3.7736

Max Act: 3.3933. Min Act: -0.0000

Data Index: 989332 (The Pile)

Max Activating Token Index: 445

Text #6

Max Range: 3.7736. Min Range: -3.7736

Max Act: 3.1352. Min Act: -0.0000

Data Index: 279249 (The Pile)

Max Activating Token Index: 435

Text #7

Max Range: 3.7736. Min Range: -3.7736

Max Act: 3.5308. Min Act: -0.0000

Data Index: 293455 (The Pile)

Max Activating Token Index: 721

Text #8

Max Range: 3.7736. Min Range: -3.7736

Max Act: 3.4838. Min Act: -0.0000

Data Index: 690116 (The Pile)

Max Activating Token Index: 472

Text #9

Max Range: 3.7736. Min Range: -3.7736

Max Act: 3.1699. Min Act: -0.0000

Data Index: 480274 (The Pile)

Max Activating Token Index: 624

Text #10

Max Range: 3.7736. Min Range: -3.7736

Max Act: 3.2699. Min Act: -0.0000

Data Index: 643760 (The Pile)

Max Activating Token Index: 619

Text #11

Max Range: 3.7736. Min Range: -3.7736

Max Act: 3.2685. Min Act: -0.0000

Data Index: 1072722 (The Pile)

Max Activating Token Index: 404

Text #12

Max Range: 3.7736. Min Range: -3.7736

Max Act: 3.2187. Min Act: -0.0000

Data Index: 271523 (The Pile)

Max Activating Token Index: 943

Text #13

Max Range: 3.7736. Min Range: -3.7736

Max Act: 3.3508. Min Act: -0.0000

Data Index: 1933650 (The Pile)

Max Activating Token Index: 836

Text #14

Max Range: 3.7736. Min Range: -3.7736

Max Act: 3.0052. Min Act: -0.0000

Data Index: 257023 (The Pile)

Max Activating Token Index: 878

Text #15

Max Range: 3.7736. Min Range: -3.7736

Max Act: 3.3414. Min Act: -0.0000

Data Index: 1605248 (The Pile)

Max Activating Token Index: 396

Text #16

Max Range: 3.7736. Min Range: -3.7736

Max Act: 2.9269. Min Act: -0.0000

Data Index: 116904 (The Pile)

Max Activating Token Index: 819

Text #17

Max Range: 3.7736. Min Range: -3.7736

Max Act: 3.2064. Min Act: -0.0000

Data Index: 319706 (The Pile)

Max Activating Token Index: 347

Text #18

Max Range: 3.7736. Min Range: -3.7736

Max Act: 3.0457. Min Act: -0.0000

Data Index: 549768 (The Pile)

Max Activating Token Index: 573

Text #19

Max Range: 3.7736. Min Range: -3.7736

Max Act: 3.2027. Min Act: -0.0000

Data Index: 225346 (The Pile)

Max Activating Token Index: 500