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

Dataset: The Pile

Neuron 3633 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.6647. Min Act: -0.0000

Data Index: 882475 (The Pile)

Max Activating Token Index: 126

Text #1

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.6814. Min Act: -0.0000

Data Index: 32644 (The Pile)

Max Activating Token Index: 866

Text #2

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.6757. Min Act: -0.0000

Data Index: 538256 (The Pile)

Max Activating Token Index: 138

Text #3

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.6294. Min Act: -0.0000

Data Index: 678886 (The Pile)

Max Activating Token Index: 91

Text #4

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.6246. Min Act: -0.0000

Data Index: 1842082 (The Pile)

Max Activating Token Index: 317

Text #5

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.6151. Min Act: -0.0000

Data Index: 881847 (The Pile)

Max Activating Token Index: 430

Text #6

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.6077. Min Act: -0.0000

Data Index: 1446793 (The Pile)

Max Activating Token Index: 510

Text #7

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.6047. Min Act: -0.0000

Data Index: 1022133 (The Pile)

Max Activating Token Index: 992

Text #8

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.5618. Min Act: -0.0000

Data Index: 1730713 (The Pile)

Max Activating Token Index: 831

Text #9

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.5597. Min Act: -0.0000

Data Index: 80438 (The Pile)

Max Activating Token Index: 815

Text #10

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.5543. Min Act: -0.0000

Data Index: 1545465 (The Pile)

Max Activating Token Index: 1004

Text #11

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.5186. Min Act: -0.0000

Data Index: 877025 (The Pile)

Max Activating Token Index: 515

Text #12

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.5744. Min Act: -0.0000

Data Index: 653263 (The Pile)

Max Activating Token Index: 809

Text #13

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.5186. Min Act: -0.0000

Data Index: 389742 (The Pile)

Max Activating Token Index: 201

Text #14

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.5632. Min Act: -0.0000

Data Index: 1577510 (The Pile)

Max Activating Token Index: 700

Text #15

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.5557. Min Act: -0.0000

Data Index: 817778 (The Pile)

Max Activating Token Index: 762

Text #16

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.5751. Min Act: -0.0000

Data Index: 1515678 (The Pile)

Max Activating Token Index: 940

Text #17

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.5460. Min Act: -0.0000

Data Index: 1777782 (The Pile)

Max Activating Token Index: 237

Text #18

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.4993. Min Act: -0.0000

Data Index: 1492592 (The Pile)

Max Activating Token Index: 1015

Text #19

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.5425. Min Act: -0.0000

Data Index: 12378 (The Pile)

Max Activating Token Index: 559