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

Dataset: The Pile

Neuron 1032 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: 1.4562. Min Range: -1.4562

Max Act: 1.4562. Min Act: 0.0000

Data Index: 1107921 (The Pile)

Max Activating Token Index: 358

Text #1

Max Range: 1.4562. Min Range: -1.4562

Max Act: 1.4486. Min Act: -0.0000

Data Index: 153664 (The Pile)

Max Activating Token Index: 479

Text #2

Max Range: 1.4562. Min Range: -1.4562

Max Act: 1.3619. Min Act: 0.0000

Data Index: 676739 (The Pile)

Max Activating Token Index: 402

Text #3

Max Range: 1.4562. Min Range: -1.4562

Max Act: 1.3314. Min Act: -0.0000

Data Index: 178777 (The Pile)

Max Activating Token Index: 611

Text #4

Max Range: 1.4562. Min Range: -1.4562

Max Act: 1.3937. Min Act: -0.0000

Data Index: 360783 (The Pile)

Max Activating Token Index: 893

Text #5

Max Range: 1.4562. Min Range: -1.4562

Max Act: 1.2855. Min Act: -0.0000

Data Index: 736340 (The Pile)

Max Activating Token Index: 758

Text #6

Max Range: 1.4562. Min Range: -1.4562

Max Act: 1.2255. Min Act: -0.0000

Data Index: 1334929 (The Pile)

Max Activating Token Index: 760

Text #7

Max Range: 1.4562. Min Range: -1.4562

Max Act: 1.2107. Min Act: -0.0000

Data Index: 1368290 (The Pile)

Max Activating Token Index: 929

Text #8

Max Range: 1.4562. Min Range: -1.4562

Max Act: 1.0595. Min Act: -0.0000

Data Index: 1557924 (The Pile)

Max Activating Token Index: 376

Text #9

Max Range: 1.4562. Min Range: -1.4562

Max Act: 1.0694. Min Act: -0.0000

Data Index: 1649797 (The Pile)

Max Activating Token Index: 789

Text #10

Max Range: 1.4562. Min Range: -1.4562

Max Act: 1.0497. Min Act: -0.0000

Data Index: 191922 (The Pile)

Max Activating Token Index: 283

Text #11

Max Range: 1.4562. Min Range: -1.4562

Max Act: 0.9749. Min Act: -0.0000

Data Index: 1403811 (The Pile)

Max Activating Token Index: 709

Text #12

Max Range: 1.4562. Min Range: -1.4562

Max Act: 0.9190. Min Act: -0.0000

Data Index: 810444 (The Pile)

Max Activating Token Index: 878

Text #13

Max Range: 1.4562. Min Range: -1.4562

Max Act: 1.0989. Min Act: -0.0000

Data Index: 1854665 (The Pile)

Max Activating Token Index: 803

Text #14

Max Range: 1.4562. Min Range: -1.4562

Max Act: 0.9807. Min Act: 0.0000

Data Index: 885094 (The Pile)

Max Activating Token Index: 906

Text #15

Max Range: 1.4562. Min Range: -1.4562

Max Act: 0.9631. Min Act: -0.0000

Data Index: 439523 (The Pile)

Max Activating Token Index: 604

Text #16

Max Range: 1.4562. Min Range: -1.4562

Max Act: 0.9510. Min Act: -0.0000

Data Index: 103782 (The Pile)

Max Activating Token Index: 396

Text #17

Max Range: 1.4562. Min Range: -1.4562

Max Act: 0.9399. Min Act: -0.0000

Data Index: 238261 (The Pile)

Max Activating Token Index: 433

Text #18

Max Range: 1.4562. Min Range: -1.4562

Max Act: 0.9927. Min Act: -0.0000

Data Index: 1455004 (The Pile)

Max Activating Token Index: 576

Text #19

Max Range: 1.4562. Min Range: -1.4562

Max Act: 0.9494. Min Act: -0.0000

Data Index: 1535557 (The Pile)

Max Activating Token Index: 918