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

Dataset: The Pile

Neuron 1277 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: 0.6434. Min Range: -0.6434

Max Act: 0.6434. Min Act: -0.0000

Data Index: 401521 (The Pile)

Max Activating Token Index: 890

Text #1

Max Range: 0.6434. Min Range: -0.6434

Max Act: 0.6246. Min Act: -0.0000

Data Index: 1229363 (The Pile)

Max Activating Token Index: 104

Text #2

Max Range: 0.6434. Min Range: -0.6434

Max Act: 0.5887. Min Act: 0.0000

Data Index: 1187299 (The Pile)

Max Activating Token Index: 523

Text #3

Max Range: 0.6434. Min Range: -0.6434

Max Act: 0.5383. Min Act: -0.0000

Data Index: 1961154 (The Pile)

Max Activating Token Index: 998

Text #4

Max Range: 0.6434. Min Range: -0.6434

Max Act: 0.5602. Min Act: 0.0000

Data Index: 341550 (The Pile)

Max Activating Token Index: 904

Text #5

Max Range: 0.6434. Min Range: -0.6434

Max Act: 0.5726. Min Act: -0.0000

Data Index: 1230871 (The Pile)

Max Activating Token Index: 411

Text #6

Max Range: 0.6434. Min Range: -0.6434

Max Act: 0.5620. Min Act: 0.0001

Data Index: 945239 (The Pile)

Max Activating Token Index: 414

Text #7

Max Range: 0.6434. Min Range: -0.6434

Max Act: 0.5207. Min Act: -0.0000

Data Index: 1422477 (The Pile)

Max Activating Token Index: 813

Text #8

Max Range: 0.6434. Min Range: -0.6434

Max Act: 0.5514. Min Act: -0.0000

Data Index: 1196883 (The Pile)

Max Activating Token Index: 284

Text #9

Max Range: 0.6434. Min Range: -0.6434

Max Act: 0.5277. Min Act: 0.0001

Data Index: 1829272 (The Pile)

Max Activating Token Index: 51

Text #10

Max Range: 0.6434. Min Range: -0.6434

Max Act: 0.5019. Min Act: -0.0000

Data Index: 1437126 (The Pile)

Max Activating Token Index: 1018

Text #11

Max Range: 0.6434. Min Range: -0.6434

Max Act: 0.5040. Min Act: -0.0000

Data Index: 997058 (The Pile)

Max Activating Token Index: 780

Text #12

Max Range: 0.6434. Min Range: -0.6434

Max Act: 0.4966. Min Act: -0.0000

Data Index: 1133259 (The Pile)

Max Activating Token Index: 796

Text #13

Max Range: 0.6434. Min Range: -0.6434

Max Act: 0.5102. Min Act: -0.0000

Data Index: 878779 (The Pile)

Max Activating Token Index: 922

Text #14

Max Range: 0.6434. Min Range: -0.6434

Max Act: 0.5078. Min Act: 0.0000

Data Index: 1914119 (The Pile)

Max Activating Token Index: 455

Text #15

Max Range: 0.6434. Min Range: -0.6434

Max Act: 0.4936. Min Act: -0.0000

Data Index: 909146 (The Pile)

Max Activating Token Index: 509

Text #16

Max Range: 0.6434. Min Range: -0.6434

Max Act: 0.4982. Min Act: -0.0000

Data Index: 1228418 (The Pile)

Max Activating Token Index: 784

Text #17

Max Range: 0.6434. Min Range: -0.6434

Max Act: 0.4982. Min Act: -0.0000

Data Index: 457149 (The Pile)

Max Activating Token Index: 388

Text #18

Max Range: 0.6434. Min Range: -0.6434

Max Act: 0.4897. Min Act: 0.0000

Data Index: 450688 (The Pile)

Max Activating Token Index: 477

Text #19

Max Range: 0.6434. Min Range: -0.6434

Max Act: 0.4749. Min Act: -0.0000

Data Index: 1177933 (The Pile)

Max Activating Token Index: 50