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

Dataset: The Pile

Neuron 2916 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: 3.3331. Min Range: -3.3331

Max Act: 3.3331. Min Act: -0.0000

Data Index: 238137 (The Pile)

Max Activating Token Index: 25

Text #1

Max Range: 3.3331. Min Range: -3.3331

Max Act: 3.0815. Min Act: -0.0000

Data Index: 1773866 (The Pile)

Max Activating Token Index: 949

Text #2

Max Range: 3.3331. Min Range: -3.3331

Max Act: 3.0626. Min Act: -0.0000

Data Index: 1228500 (The Pile)

Max Activating Token Index: 514

Text #3

Max Range: 3.3331. Min Range: -3.3331

Max Act: 2.7319. Min Act: -0.0000

Data Index: 1082519 (The Pile)

Max Activating Token Index: 422

Text #4

Max Range: 3.3331. Min Range: -3.3331

Max Act: 2.6960. Min Act: -0.0000

Data Index: 1864626 (The Pile)

Max Activating Token Index: 743

Text #5

Max Range: 3.3331. Min Range: -3.3331

Max Act: 2.8871. Min Act: -0.0000

Data Index: 1046163 (The Pile)

Max Activating Token Index: 58

Text #6

Max Range: 3.3331. Min Range: -3.3331

Max Act: 2.8473. Min Act: -0.0000

Data Index: 1687000 (The Pile)

Max Activating Token Index: 364

Text #7

Max Range: 3.3331. Min Range: -3.3331

Max Act: 2.1670. Min Act: -0.0001

Data Index: 1759927 (The Pile)

Max Activating Token Index: 932

Text #8

Max Range: 3.3331. Min Range: -3.3331

Max Act: 2.6183. Min Act: -0.0000

Data Index: 77743 (The Pile)

Max Activating Token Index: 1008

Text #9

Max Range: 3.3331. Min Range: -3.3331

Max Act: 2.3256. Min Act: -0.0000

Data Index: 199500 (The Pile)

Max Activating Token Index: 279

Text #10

Max Range: 3.3331. Min Range: -3.3331

Max Act: 2.5510. Min Act: -0.0000

Data Index: 703569 (The Pile)

Max Activating Token Index: 442

Text #11

Max Range: 3.3331. Min Range: -3.3331

Max Act: 2.5453. Min Act: -0.0000

Data Index: 789455 (The Pile)

Max Activating Token Index: 786

Text #12

Max Range: 3.3331. Min Range: -3.3331

Max Act: 2.5416. Min Act: -0.0000

Data Index: 1768585 (The Pile)

Max Activating Token Index: 24

Text #13

Max Range: 3.3331. Min Range: -3.3331

Max Act: 2.2433. Min Act: -0.0000

Data Index: 254998 (The Pile)

Max Activating Token Index: 263

Text #14

Max Range: 3.3331. Min Range: -3.3331

Max Act: 2.5121. Min Act: -0.0000

Data Index: 1433452 (The Pile)

Max Activating Token Index: 851

Text #15

Max Range: 3.3331. Min Range: -3.3331

Max Act: 2.4837. Min Act: -0.0000

Data Index: 994578 (The Pile)

Max Activating Token Index: 98

Text #16

Max Range: 3.3331. Min Range: -3.3331

Max Act: 2.4188. Min Act: -0.0000

Data Index: 25396 (The Pile)

Max Activating Token Index: 610

Text #17

Max Range: 3.3331. Min Range: -3.3331

Max Act: 2.4965. Min Act: -0.0000

Data Index: 1601354 (The Pile)

Max Activating Token Index: 98

Text #18

Max Range: 3.3331. Min Range: -3.3331

Max Act: 2.4981. Min Act: -0.0000

Data Index: 551672 (The Pile)

Max Activating Token Index: 429

Text #19

Max Range: 3.3331. Min Range: -3.3331

Max Act: 2.2759. Min Act: -0.0000

Data Index: 1844839 (The Pile)

Max Activating Token Index: 385