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

Dataset: The Pile

Neuron 2657 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3688. Min Range: -1.3688

Max Act: 1.3688. Min Act: -0.0000

Data Index: 412410 (The Pile)

Max Activating Token Index: 758

Text #1

Max Range: 1.3688. Min Range: -1.3688

Max Act: 1.1960. Min Act: -0.0000

Data Index: 408761 (The Pile)

Max Activating Token Index: 473

Text #2

Max Range: 1.3688. Min Range: -1.3688

Max Act: 1.2960. Min Act: -0.0000

Data Index: 1763675 (The Pile)

Max Activating Token Index: 588

Text #3

Max Range: 1.3688. Min Range: -1.3688

Max Act: 1.2420. Min Act: -0.0000

Data Index: 819957 (The Pile)

Max Activating Token Index: 944

Text #4

Max Range: 1.3688. Min Range: -1.3688

Max Act: 1.1428. Min Act: -0.0000

Data Index: 1451763 (The Pile)

Max Activating Token Index: 250

Text #5

Max Range: 1.3688. Min Range: -1.3688

Max Act: 1.1943. Min Act: -0.0000

Data Index: 1786077 (The Pile)

Max Activating Token Index: 463

Text #6

Max Range: 1.3688. Min Range: -1.3688

Max Act: 1.2116. Min Act: -0.0000

Data Index: 1906501 (The Pile)

Max Activating Token Index: 564

Text #7

Max Range: 1.3688. Min Range: -1.3688

Max Act: 1.0805. Min Act: -0.0000

Data Index: 373683 (The Pile)

Max Activating Token Index: 138

Text #8

Max Range: 1.3688. Min Range: -1.3688

Max Act: 1.1062. Min Act: -0.0000

Data Index: 1705171 (The Pile)

Max Activating Token Index: 736

Text #9

Max Range: 1.3688. Min Range: -1.3688

Max Act: 1.1407. Min Act: -0.0000

Data Index: 1691624 (The Pile)

Max Activating Token Index: 517

Text #10

Max Range: 1.3688. Min Range: -1.3688

Max Act: 1.1118. Min Act: -0.0000

Data Index: 633912 (The Pile)

Max Activating Token Index: 941

Text #11

Max Range: 1.3688. Min Range: -1.3688

Max Act: 1.1119. Min Act: -0.0000

Data Index: 55262 (The Pile)

Max Activating Token Index: 623

Text #12

Max Range: 1.3688. Min Range: -1.3688

Max Act: 1.0595. Min Act: -0.0000

Data Index: 389648 (The Pile)

Max Activating Token Index: 413

Text #13

Max Range: 1.3688. Min Range: -1.3688

Max Act: 1.0927. Min Act: -0.0000

Data Index: 1507015 (The Pile)

Max Activating Token Index: 670

Text #14

Max Range: 1.3688. Min Range: -1.3688

Max Act: 1.1224. Min Act: -0.0000

Data Index: 15009 (The Pile)

Max Activating Token Index: 700

Text #15

Max Range: 1.3688. Min Range: -1.3688

Max Act: 1.0735. Min Act: -0.0000

Data Index: 1971740 (The Pile)

Max Activating Token Index: 793

Text #16

Max Range: 1.3688. Min Range: -1.3688

Max Act: 1.0562. Min Act: -0.0000

Data Index: 557502 (The Pile)

Max Activating Token Index: 908

Text #17

Max Range: 1.3688. Min Range: -1.3688

Max Act: 1.0355. Min Act: -0.0000

Data Index: 1056538 (The Pile)

Max Activating Token Index: 644

Text #18

Max Range: 1.3688. Min Range: -1.3688

Max Act: 1.1087. Min Act: -0.0000

Data Index: 313327 (The Pile)

Max Activating Token Index: 926

Text #19

Max Range: 1.3688. Min Range: -1.3688

Max Act: 1.1040. Min Act: -0.0000

Data Index: 1421085 (The Pile)

Max Activating Token Index: 931