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

Dataset: The Pile

Neuron 4728 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: 0.8725. Min Range: -0.8725

Max Act: 0.8725. Min Act: -0.0000

Data Index: 834670 (The Pile)

Max Activating Token Index: 735

Text #1

Max Range: 0.8725. Min Range: -0.8725

Max Act: 0.8344. Min Act: -0.0000

Data Index: 1742923 (The Pile)

Max Activating Token Index: 125

Text #2

Max Range: 0.8725. Min Range: -0.8725

Max Act: 0.7856. Min Act: -0.0000

Data Index: 949134 (The Pile)

Max Activating Token Index: 459

Text #3

Max Range: 0.8725. Min Range: -0.8725

Max Act: 0.7628. Min Act: 0.0000

Data Index: 1235386 (The Pile)

Max Activating Token Index: 20

Text #4

Max Range: 0.8725. Min Range: -0.8725

Max Act: 0.7513. Min Act: -0.0000

Data Index: 708809 (The Pile)

Max Activating Token Index: 83

Text #5

Max Range: 0.8725. Min Range: -0.8725

Max Act: 0.7181. Min Act: -0.0000

Data Index: 903530 (The Pile)

Max Activating Token Index: 1010

Text #6

Max Range: 0.8725. Min Range: -0.8725

Max Act: 0.7266. Min Act: -0.0000

Data Index: 1095725 (The Pile)

Max Activating Token Index: 888

Text #7

Max Range: 0.8725. Min Range: -0.8725

Max Act: 0.7305. Min Act: -0.0000

Data Index: 665565 (The Pile)

Max Activating Token Index: 200

Text #8

Max Range: 0.8725. Min Range: -0.8725

Max Act: 0.7512. Min Act: -0.0000

Data Index: 756552 (The Pile)

Max Activating Token Index: 653

Text #9

Max Range: 0.8725. Min Range: -0.8725

Max Act: 0.7127. Min Act: 0.0000

Data Index: 1138036 (The Pile)

Max Activating Token Index: 50

Text #10

Max Range: 0.8725. Min Range: -0.8725

Max Act: 0.7084. Min Act: -0.0000

Data Index: 1271582 (The Pile)

Max Activating Token Index: 28

Text #11

Max Range: 0.8725. Min Range: -0.8725

Max Act: 0.6995. Min Act: -0.0000

Data Index: 1191150 (The Pile)

Max Activating Token Index: 495

Text #12

Max Range: 0.8725. Min Range: -0.8725

Max Act: 0.6839. Min Act: 0.0000

Data Index: 1411721 (The Pile)

Max Activating Token Index: 33

Text #13

Max Range: 0.8725. Min Range: -0.8725

Max Act: 0.6813. Min Act: -0.0000

Data Index: 118113 (The Pile)

Max Activating Token Index: 305

Text #14

Max Range: 0.8725. Min Range: -0.8725

Max Act: 0.6783. Min Act: -0.0000

Data Index: 1201993 (The Pile)

Max Activating Token Index: 503

Text #15

Max Range: 0.8725. Min Range: -0.8725

Max Act: 0.6673. Min Act: -0.0000

Data Index: 1190409 (The Pile)

Max Activating Token Index: 866

Text #16

Max Range: 0.8725. Min Range: -0.8725

Max Act: 0.6668. Min Act: -0.0000

Data Index: 977474 (The Pile)

Max Activating Token Index: 794

Text #17

Max Range: 0.8725. Min Range: -0.8725

Max Act: 0.6629. Min Act: -0.0000

Data Index: 1876301 (The Pile)

Max Activating Token Index: 169

Text #18

Max Range: 0.8725. Min Range: -0.8725

Max Act: 0.6770. Min Act: -0.0000

Data Index: 1830775 (The Pile)

Max Activating Token Index: 430

Text #19

Max Range: 0.8725. Min Range: -0.8725

Max Act: 0.6395. Min Act: -0.0000

Data Index: 338573 (The Pile)

Max Activating Token Index: 498