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

Dataset: The Pile

Neuron 466 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: 3.9002. Min Range: -3.9002

Max Act: 3.9002. Min Act: -0.0000

Data Index: 1466515 (The Pile)

Max Activating Token Index: 804

Text #1

Max Range: 3.9002. Min Range: -3.9002

Max Act: 3.8958. Min Act: -0.0000

Data Index: 1280543 (The Pile)

Max Activating Token Index: 539

Text #2

Max Range: 3.9002. Min Range: -3.9002

Max Act: 3.5693. Min Act: -0.0000

Data Index: 500843 (The Pile)

Max Activating Token Index: 976

Text #3

Max Range: 3.9002. Min Range: -3.9002

Max Act: 3.4814. Min Act: -0.0000

Data Index: 1476102 (The Pile)

Max Activating Token Index: 566

Text #4

Max Range: 3.9002. Min Range: -3.9002

Max Act: 3.4716. Min Act: -0.0000

Data Index: 149504 (The Pile)

Max Activating Token Index: 476

Text #5

Max Range: 3.9002. Min Range: -3.9002

Max Act: 3.3260. Min Act: -0.0000

Data Index: 1844505 (The Pile)

Max Activating Token Index: 395

Text #6

Max Range: 3.9002. Min Range: -3.9002

Max Act: 3.4584. Min Act: -0.0000

Data Index: 1611599 (The Pile)

Max Activating Token Index: 982

Text #7

Max Range: 3.9002. Min Range: -3.9002

Max Act: 3.1152. Min Act: -0.0000

Data Index: 1951908 (The Pile)

Max Activating Token Index: 730

Text #8

Max Range: 3.9002. Min Range: -3.9002

Max Act: 2.9805. Min Act: -0.0000

Data Index: 1124930 (The Pile)

Max Activating Token Index: 532

Text #9

Max Range: 3.9002. Min Range: -3.9002

Max Act: 2.9720. Min Act: -0.0000

Data Index: 767912 (The Pile)

Max Activating Token Index: 731

Text #10

Max Range: 3.9002. Min Range: -3.9002

Max Act: 3.1162. Min Act: -0.0000

Data Index: 1376171 (The Pile)

Max Activating Token Index: 903

Text #11

Max Range: 3.9002. Min Range: -3.9002

Max Act: 3.0863. Min Act: -0.0000

Data Index: 1576441 (The Pile)

Max Activating Token Index: 441

Text #12

Max Range: 3.9002. Min Range: -3.9002

Max Act: 3.2246. Min Act: -0.0000

Data Index: 833064 (The Pile)

Max Activating Token Index: 336

Text #13

Max Range: 3.9002. Min Range: -3.9002

Max Act: 3.0655. Min Act: -0.0000

Data Index: 1649087 (The Pile)

Max Activating Token Index: 1005

Text #14

Max Range: 3.9002. Min Range: -3.9002

Max Act: 2.9316. Min Act: -0.0000

Data Index: 690069 (The Pile)

Max Activating Token Index: 284

Text #15

Max Range: 3.9002. Min Range: -3.9002

Max Act: 3.0323. Min Act: -0.0000

Data Index: 1104739 (The Pile)

Max Activating Token Index: 990

Text #16

Max Range: 3.9002. Min Range: -3.9002

Max Act: 2.9025. Min Act: -0.0000

Data Index: 1941743 (The Pile)

Max Activating Token Index: 828

Text #17

Max Range: 3.9002. Min Range: -3.9002

Max Act: 2.9816. Min Act: -0.0000

Data Index: 646160 (The Pile)

Max Activating Token Index: 707

Text #18

Max Range: 3.9002. Min Range: -3.9002

Max Act: 2.9677. Min Act: -0.0000

Data Index: 1557338 (The Pile)

Max Activating Token Index: 834

Text #19

Max Range: 3.9002. Min Range: -3.9002

Max Act: 2.9765. Min Act: -0.0000

Data Index: 289502 (The Pile)

Max Activating Token Index: 547