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

Dataset: The Pile

Neuron 409 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: 0.7373. Min Range: -0.7373

Max Act: 0.7254. Min Act: -0.0000

Data Index: 905677 (The Pile)

Max Activating Token Index: 540

Text #1

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.7373. Min Act: -0.0000

Data Index: 1110323 (The Pile)

Max Activating Token Index: 928

Text #2

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.7055. Min Act: -0.0000

Data Index: 573009 (The Pile)

Max Activating Token Index: 128

Text #3

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.6302. Min Act: -0.0000

Data Index: 1063461 (The Pile)

Max Activating Token Index: 908

Text #4

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.6160. Min Act: -0.0000

Data Index: 1109961 (The Pile)

Max Activating Token Index: 907

Text #5

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.5838. Min Act: -0.0000

Data Index: 248383 (The Pile)

Max Activating Token Index: 898

Text #6

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.5854. Min Act: -0.0000

Data Index: 123548 (The Pile)

Max Activating Token Index: 982

Text #7

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.6277. Min Act: -0.0000

Data Index: 941949 (The Pile)

Max Activating Token Index: 881

Text #8

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.6772. Min Act: -0.0000

Data Index: 55657 (The Pile)

Max Activating Token Index: 931

Text #9

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.6514. Min Act: -0.0000

Data Index: 128843 (The Pile)

Max Activating Token Index: 827

Text #10

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.6012. Min Act: -0.0000

Data Index: 279632 (The Pile)

Max Activating Token Index: 571

Text #11

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.5803. Min Act: -0.0000

Data Index: 318006 (The Pile)

Max Activating Token Index: 849

Text #12

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.5505. Min Act: -0.0000

Data Index: 996528 (The Pile)

Max Activating Token Index: 398

Text #13

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.6032. Min Act: -0.0000

Data Index: 1872192 (The Pile)

Max Activating Token Index: 933

Text #14

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.5847. Min Act: -0.0000

Data Index: 1615009 (The Pile)

Max Activating Token Index: 659

Text #15

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.5755. Min Act: -0.0000

Data Index: 446032 (The Pile)

Max Activating Token Index: 902

Text #16

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.6284. Min Act: -0.0000

Data Index: 708508 (The Pile)

Max Activating Token Index: 559

Text #17

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.5887. Min Act: -0.0000

Data Index: 713775 (The Pile)

Max Activating Token Index: 955

Text #18

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.5383. Min Act: -0.0000

Data Index: 1179376 (The Pile)

Max Activating Token Index: 912

Text #19

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.5340. Min Act: -0.0000

Data Index: 276250 (The Pile)

Max Activating Token Index: 998