Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 3303 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.3114. Min Range: -0.3114

Max Act: 0.3114. Min Act: -0.0000

Data Index: 96296 (The Pile)

Max Activating Token Index: 499

Text #1

Max Range: 0.3114. Min Range: -0.3114

Max Act: 0.2791. Min Act: -0.0000

Data Index: 1049703 (The Pile)

Max Activating Token Index: 340

Text #2

Max Range: 0.3114. Min Range: -0.3114

Max Act: 0.2845. Min Act: -0.0000

Data Index: 1007052 (The Pile)

Max Activating Token Index: 554

Text #3

Max Range: 0.3114. Min Range: -0.3114

Max Act: 0.2338. Min Act: -0.0000

Data Index: 1684475 (The Pile)

Max Activating Token Index: 781

Text #4

Max Range: 0.3114. Min Range: -0.3114

Max Act: 0.1920. Min Act: -0.0000

Data Index: 1339263 (The Pile)

Max Activating Token Index: 304

Text #5

Max Range: 0.3114. Min Range: -0.3114

Max Act: 0.2216. Min Act: -0.0000

Data Index: 1300619 (The Pile)

Max Activating Token Index: 214

Text #6

Max Range: 0.3114. Min Range: -0.3114

Max Act: 0.2350. Min Act: -0.0000

Data Index: 1952285 (The Pile)

Max Activating Token Index: 207

Text #7

Max Range: 0.3114. Min Range: -0.3114

Max Act: 0.2208. Min Act: -0.0000

Data Index: 1724336 (The Pile)

Max Activating Token Index: 483

Text #8

Max Range: 0.3114. Min Range: -0.3114

Max Act: 0.2154. Min Act: -0.0000

Data Index: 1240428 (The Pile)

Max Activating Token Index: 335

Text #9

Max Range: 0.3114. Min Range: -0.3114

Max Act: 0.2026. Min Act: -0.0000

Data Index: 1186583 (The Pile)

Max Activating Token Index: 738

Text #10

Max Range: 0.3114. Min Range: -0.3114

Max Act: 0.2037. Min Act: -0.0000

Data Index: 340267 (The Pile)

Max Activating Token Index: 296

Text #11

Max Range: 0.3114. Min Range: -0.3114

Max Act: 0.1786. Min Act: -0.0000

Data Index: 1885791 (The Pile)

Max Activating Token Index: 84

Text #12

Max Range: 0.3114. Min Range: -0.3114

Max Act: 0.1921. Min Act: -0.0000

Data Index: 328765 (The Pile)

Max Activating Token Index: 401

Text #13

Max Range: 0.3114. Min Range: -0.3114

Max Act: 0.1686. Min Act: -0.0000

Data Index: 1275199 (The Pile)

Max Activating Token Index: 304

Text #14

Max Range: 0.3114. Min Range: -0.3114

Max Act: 0.1847. Min Act: -0.0000

Data Index: 1456056 (The Pile)

Max Activating Token Index: 58

Text #15

Max Range: 0.3114. Min Range: -0.3114

Max Act: 0.1856. Min Act: -0.0000

Data Index: 460013 (The Pile)

Max Activating Token Index: 523

Text #16

Max Range: 0.3114. Min Range: -0.3114

Max Act: 0.1760. Min Act: -0.0000

Data Index: 1853089 (The Pile)

Max Activating Token Index: 406

Text #17

Max Range: 0.3114. Min Range: -0.3114

Max Act: 0.1763. Min Act: -0.0000

Data Index: 320606 (The Pile)

Max Activating Token Index: 59

Text #18

Max Range: 0.3114. Min Range: -0.3114

Max Act: 0.1759. Min Act: -0.0000

Data Index: 1973618 (The Pile)

Max Activating Token Index: 190

Text #19

Max Range: 0.3114. Min Range: -0.3114

Max Act: 0.1754. Min Act: -0.0000

Data Index: 1932121 (The Pile)

Max Activating Token Index: 34