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

Dataset: The Pile

Neuron 2318 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 11.4848. Min Range: -11.4848

Max Act: 11.4848. Min Act: -0.0000

Data Index: 1151204 (The Pile)

Max Activating Token Index: 972

Text #1

Max Range: 11.4848. Min Range: -11.4848

Max Act: 11.3229. Min Act: -0.0000

Data Index: 985421 (The Pile)

Max Activating Token Index: 215

Text #2

Max Range: 11.4848. Min Range: -11.4848

Max Act: 10.6229. Min Act: -0.0000

Data Index: 190409 (The Pile)

Max Activating Token Index: 180

Text #3

Max Range: 11.4848. Min Range: -11.4848

Max Act: 10.6722. Min Act: -0.0000

Data Index: 1315556 (The Pile)

Max Activating Token Index: 892

Text #4

Max Range: 11.4848. Min Range: -11.4848

Max Act: 10.6380. Min Act: -0.0000

Data Index: 105917 (The Pile)

Max Activating Token Index: 930

Text #5

Max Range: 11.4848. Min Range: -11.4848

Max Act: 10.6895. Min Act: -0.0000

Data Index: 1441823 (The Pile)

Max Activating Token Index: 903

Text #6

Max Range: 11.4848. Min Range: -11.4848

Max Act: 10.6545. Min Act: -0.0000

Data Index: 1735471 (The Pile)

Max Activating Token Index: 931

Text #7

Max Range: 11.4848. Min Range: -11.4848

Max Act: 10.6193. Min Act: -0.0000

Data Index: 1582712 (The Pile)

Max Activating Token Index: 160

Text #8

Max Range: 11.4848. Min Range: -11.4848

Max Act: 10.8667. Min Act: -0.0000

Data Index: 188220 (The Pile)

Max Activating Token Index: 459

Text #9

Max Range: 11.4848. Min Range: -11.4848

Max Act: 10.5902. Min Act: -0.0000

Data Index: 550395 (The Pile)

Max Activating Token Index: 522

Text #10

Max Range: 11.4848. Min Range: -11.4848

Max Act: 10.6835. Min Act: -0.0000

Data Index: 1232950 (The Pile)

Max Activating Token Index: 791

Text #11

Max Range: 11.4848. Min Range: -11.4848

Max Act: 10.8800. Min Act: -0.0000

Data Index: 1852207 (The Pile)

Max Activating Token Index: 960

Text #12

Max Range: 11.4848. Min Range: -11.4848

Max Act: 10.7354. Min Act: -0.0000

Data Index: 1748004 (The Pile)

Max Activating Token Index: 997

Text #13

Max Range: 11.4848. Min Range: -11.4848

Max Act: 10.5541. Min Act: -0.0000

Data Index: 1594694 (The Pile)

Max Activating Token Index: 817

Text #14

Max Range: 11.4848. Min Range: -11.4848

Max Act: 10.4841. Min Act: -0.0000

Data Index: 66258 (The Pile)

Max Activating Token Index: 804

Text #15

Max Range: 11.4848. Min Range: -11.4848

Max Act: 10.3513. Min Act: -0.0000

Data Index: 665701 (The Pile)

Max Activating Token Index: 921

Text #16

Max Range: 11.4848. Min Range: -11.4848

Max Act: 10.6131. Min Act: -0.0000

Data Index: 304371 (The Pile)

Max Activating Token Index: 914

Text #17

Max Range: 11.4848. Min Range: -11.4848

Max Act: 10.3071. Min Act: -0.0000

Data Index: 1276222 (The Pile)

Max Activating Token Index: 649

Text #18

Max Range: 11.4848. Min Range: -11.4848

Max Act: 10.5605. Min Act: -0.0000

Data Index: 13626 (The Pile)

Max Activating Token Index: 605

Text #19

Max Range: 11.4848. Min Range: -11.4848

Max Act: 10.5765. Min Act: -0.0000

Data Index: 1406726 (The Pile)

Max Activating Token Index: 387