Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1985 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.7567. Min Range: -0.7567

Max Act: 0.7443. Min Act: -0.0000

Data Index: 1390486 (The Pile)

Max Activating Token Index: 788

Text #1

Max Range: 0.7567. Min Range: -0.7567

Max Act: 0.7567. Min Act: -0.0000

Data Index: 896991 (The Pile)

Max Activating Token Index: 531

Text #2

Max Range: 0.7567. Min Range: -0.7567

Max Act: 0.7342. Min Act: -0.0000

Data Index: 592633 (The Pile)

Max Activating Token Index: 142

Text #3

Max Range: 0.7567. Min Range: -0.7567

Max Act: 0.7099. Min Act: -0.0000

Data Index: 25078 (The Pile)

Max Activating Token Index: 433

Text #4

Max Range: 0.7567. Min Range: -0.7567

Max Act: 0.7257. Min Act: -0.0000

Data Index: 1556395 (The Pile)

Max Activating Token Index: 939

Text #5

Max Range: 0.7567. Min Range: -0.7567

Max Act: 0.6918. Min Act: -0.0000

Data Index: 153781 (The Pile)

Max Activating Token Index: 789

Text #6

Max Range: 0.7567. Min Range: -0.7567

Max Act: 0.6751. Min Act: -0.0000

Data Index: 1864314 (The Pile)

Max Activating Token Index: 6

Text #7

Max Range: 0.7567. Min Range: -0.7567

Max Act: 0.6673. Min Act: -0.0000

Data Index: 463480 (The Pile)

Max Activating Token Index: 812

Text #8

Max Range: 0.7567. Min Range: -0.7567

Max Act: 0.7049. Min Act: -0.0000

Data Index: 836584 (The Pile)

Max Activating Token Index: 936

Text #9

Max Range: 0.7567. Min Range: -0.7567

Max Act: 0.6802. Min Act: -0.0000

Data Index: 1637566 (The Pile)

Max Activating Token Index: 1011

Text #10

Max Range: 0.7567. Min Range: -0.7567

Max Act: 0.7033. Min Act: -0.0000

Data Index: 1508766 (The Pile)

Max Activating Token Index: 590

Text #11

Max Range: 0.7567. Min Range: -0.7567

Max Act: 0.6276. Min Act: -0.0000

Data Index: 124853 (The Pile)

Max Activating Token Index: 714

Text #12

Max Range: 0.7567. Min Range: -0.7567

Max Act: 0.6655. Min Act: -0.0000

Data Index: 503769 (The Pile)

Max Activating Token Index: 761

Text #13

Max Range: 0.7567. Min Range: -0.7567

Max Act: 0.6823. Min Act: -0.0000

Data Index: 454870 (The Pile)

Max Activating Token Index: 723

Text #14

Max Range: 0.7567. Min Range: -0.7567

Max Act: 0.6445. Min Act: -0.0000

Data Index: 465244 (The Pile)

Max Activating Token Index: 735

Text #15

Max Range: 0.7567. Min Range: -0.7567

Max Act: 0.6249. Min Act: -0.0000

Data Index: 1347168 (The Pile)

Max Activating Token Index: 736

Text #16

Max Range: 0.7567. Min Range: -0.7567

Max Act: 0.6541. Min Act: -0.0000

Data Index: 1962946 (The Pile)

Max Activating Token Index: 484

Text #17

Max Range: 0.7567. Min Range: -0.7567

Max Act: 0.6246. Min Act: -0.0000

Data Index: 1340884 (The Pile)

Max Activating Token Index: 720

Text #18

Max Range: 0.7567. Min Range: -0.7567

Max Act: 0.6341. Min Act: -0.0000

Data Index: 1616466 (The Pile)

Max Activating Token Index: 393

Text #19

Max Range: 0.7567. Min Range: -0.7567

Max Act: 0.6023. Min Act: -0.0000

Data Index: 1703738 (The Pile)

Max Activating Token Index: 625