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

Dataset: The Pile

Neuron 1738 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: 0.6344. Min Range: -0.6344

Max Act: 0.6344. Min Act: -0.0000

Data Index: 499569 (The Pile)

Max Activating Token Index: 837

Text #1

Max Range: 0.6344. Min Range: -0.6344

Max Act: 0.6228. Min Act: -0.0000

Data Index: 1659154 (The Pile)

Max Activating Token Index: 995

Text #2

Max Range: 0.6344. Min Range: -0.6344

Max Act: 0.5726. Min Act: -0.0000

Data Index: 1296426 (The Pile)

Max Activating Token Index: 62

Text #3

Max Range: 0.6344. Min Range: -0.6344

Max Act: 0.5757. Min Act: -0.0000

Data Index: 1648793 (The Pile)

Max Activating Token Index: 811

Text #4

Max Range: 0.6344. Min Range: -0.6344

Max Act: 0.5718. Min Act: -0.0000

Data Index: 1212787 (The Pile)

Max Activating Token Index: 834

Text #5

Max Range: 0.6344. Min Range: -0.6344

Max Act: 0.5374. Min Act: -0.0000

Data Index: 174339 (The Pile)

Max Activating Token Index: 897

Text #6

Max Range: 0.6344. Min Range: -0.6344

Max Act: 0.5459. Min Act: -0.0000

Data Index: 892048 (The Pile)

Max Activating Token Index: 977

Text #7

Max Range: 0.6344. Min Range: -0.6344

Max Act: 0.5227. Min Act: -0.0000

Data Index: 1064107 (The Pile)

Max Activating Token Index: 998

Text #8

Max Range: 0.6344. Min Range: -0.6344

Max Act: 0.5043. Min Act: -0.0000

Data Index: 712946 (The Pile)

Max Activating Token Index: 918

Text #9

Max Range: 0.6344. Min Range: -0.6344

Max Act: 0.4325. Min Act: -0.0000

Data Index: 1702183 (The Pile)

Max Activating Token Index: 875

Text #10

Max Range: 0.6344. Min Range: -0.6344

Max Act: 0.3203. Min Act: -0.0000

Data Index: 329557 (The Pile)

Max Activating Token Index: 895

Text #11

Max Range: 0.6344. Min Range: -0.6344

Max Act: 0.4157. Min Act: -0.0000

Data Index: 1047806 (The Pile)

Max Activating Token Index: 571

Text #12

Max Range: 0.6344. Min Range: -0.6344

Max Act: 0.3911. Min Act: -0.0000

Data Index: 272767 (The Pile)

Max Activating Token Index: 991

Text #13

Max Range: 0.6344. Min Range: -0.6344

Max Act: 0.4284. Min Act: -0.0000

Data Index: 165709 (The Pile)

Max Activating Token Index: 748

Text #14

Max Range: 0.6344. Min Range: -0.6344

Max Act: 0.3762. Min Act: -0.0000

Data Index: 829801 (The Pile)

Max Activating Token Index: 600

Text #15

Max Range: 0.6344. Min Range: -0.6344

Max Act: 0.3633. Min Act: -0.0000

Data Index: 1403559 (The Pile)

Max Activating Token Index: 771

Text #16

Max Range: 0.6344. Min Range: -0.6344

Max Act: 0.4038. Min Act: -0.0000

Data Index: 1630465 (The Pile)

Max Activating Token Index: 947

Text #17

Max Range: 0.6344. Min Range: -0.6344

Max Act: 0.3969. Min Act: -0.0000

Data Index: 416141 (The Pile)

Max Activating Token Index: 252

Text #18

Max Range: 0.6344. Min Range: -0.6344

Max Act: 0.3672. Min Act: -0.0000

Data Index: 1674929 (The Pile)

Max Activating Token Index: 236

Text #19

Max Range: 0.6344. Min Range: -0.6344

Max Act: 0.4002. Min Act: -0.0000

Data Index: 839613 (The Pile)

Max Activating Token Index: 722