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

Dataset: The Pile

Neuron 1905 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7395. Min Range: -0.7395

Max Act: 0.7395. Min Act: -0.0000

Data Index: 1220226 (The Pile)

Max Activating Token Index: 979

Text #1

Max Range: 0.7395. Min Range: -0.7395

Max Act: 0.5516. Min Act: -0.0000

Data Index: 1401521 (The Pile)

Max Activating Token Index: 554

Text #2

Max Range: 0.7395. Min Range: -0.7395

Max Act: 0.5069. Min Act: -0.0000

Data Index: 168665 (The Pile)

Max Activating Token Index: 978

Text #3

Max Range: 0.7395. Min Range: -0.7395

Max Act: 0.5067. Min Act: 0.0000

Data Index: 1002619 (The Pile)

Max Activating Token Index: 844

Text #4

Max Range: 0.7395. Min Range: -0.7395

Max Act: 0.4464. Min Act: -0.0000

Data Index: 519694 (The Pile)

Max Activating Token Index: 924

Text #5

Max Range: 0.7395. Min Range: -0.7395

Max Act: 0.3830. Min Act: -0.0000

Data Index: 184232 (The Pile)

Max Activating Token Index: 543

Text #6

Max Range: 0.7395. Min Range: -0.7395

Max Act: 0.4739. Min Act: -0.0000

Data Index: 1645490 (The Pile)

Max Activating Token Index: 890

Text #7

Max Range: 0.7395. Min Range: -0.7395

Max Act: 0.4683. Min Act: -0.0000

Data Index: 1893390 (The Pile)

Max Activating Token Index: 790

Text #8

Max Range: 0.7395. Min Range: -0.7395

Max Act: 0.4086. Min Act: -0.0000

Data Index: 1126910 (The Pile)

Max Activating Token Index: 813

Text #9

Max Range: 0.7395. Min Range: -0.7395

Max Act: 0.4505. Min Act: -0.0000

Data Index: 1889597 (The Pile)

Max Activating Token Index: 884

Text #10

Max Range: 0.7395. Min Range: -0.7395

Max Act: 0.4309. Min Act: -0.0000

Data Index: 497487 (The Pile)

Max Activating Token Index: 953

Text #11

Max Range: 0.7395. Min Range: -0.7395

Max Act: 0.3638. Min Act: -0.0001

Data Index: 1274950 (The Pile)

Max Activating Token Index: 956

Text #12

Max Range: 0.7395. Min Range: -0.7395

Max Act: 0.4025. Min Act: -0.0000

Data Index: 120273 (The Pile)

Max Activating Token Index: 924

Text #13

Max Range: 0.7395. Min Range: -0.7395

Max Act: 0.4051. Min Act: -0.0000

Data Index: 586984 (The Pile)

Max Activating Token Index: 964

Text #14

Max Range: 0.7395. Min Range: -0.7395

Max Act: 0.3844. Min Act: -0.0000

Data Index: 238033 (The Pile)

Max Activating Token Index: 874

Text #15

Max Range: 0.7395. Min Range: -0.7395

Max Act: 0.3597. Min Act: -0.0000

Data Index: 985590 (The Pile)

Max Activating Token Index: 673

Text #16

Max Range: 0.7395. Min Range: -0.7395

Max Act: 0.4518. Min Act: -0.0000

Data Index: 1446800 (The Pile)

Max Activating Token Index: 649

Text #17

Max Range: 0.7395. Min Range: -0.7395

Max Act: 0.4130. Min Act: -0.0000

Data Index: 474851 (The Pile)

Max Activating Token Index: 945

Text #18

Max Range: 0.7395. Min Range: -0.7395

Max Act: 0.3754. Min Act: -0.0000

Data Index: 1732061 (The Pile)

Max Activating Token Index: 928

Text #19

Max Range: 0.7395. Min Range: -0.7395

Max Act: 0.3948. Min Act: -0.0000

Data Index: 1204536 (The Pile)

Max Activating Token Index: 518