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

Dataset: The Pile

Neuron 2390 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3262. Min Range: -1.3262

Max Act: 1.3262. Min Act: -0.0000

Data Index: 473642 (The Pile)

Max Activating Token Index: 547

Text #1

Max Range: 1.3262. Min Range: -1.3262

Max Act: 1.2985. Min Act: -0.0000

Data Index: 1783398 (The Pile)

Max Activating Token Index: 338

Text #2

Max Range: 1.3262. Min Range: -1.3262

Max Act: 1.1949. Min Act: -0.0000

Data Index: 1076233 (The Pile)

Max Activating Token Index: 610

Text #3

Max Range: 1.3262. Min Range: -1.3262

Max Act: 1.0943. Min Act: -0.0000

Data Index: 595871 (The Pile)

Max Activating Token Index: 445

Text #4

Max Range: 1.3262. Min Range: -1.3262

Max Act: 0.9953. Min Act: -0.0000

Data Index: 907989 (The Pile)

Max Activating Token Index: 192

Text #5

Max Range: 1.3262. Min Range: -1.3262

Max Act: 1.0047. Min Act: -0.0000

Data Index: 600423 (The Pile)

Max Activating Token Index: 1003

Text #6

Max Range: 1.3262. Min Range: -1.3262

Max Act: 0.9124. Min Act: -0.0000

Data Index: 42726 (The Pile)

Max Activating Token Index: 211

Text #7

Max Range: 1.3262. Min Range: -1.3262

Max Act: 1.0023. Min Act: -0.0000

Data Index: 883343 (The Pile)

Max Activating Token Index: 753

Text #8

Max Range: 1.3262. Min Range: -1.3262

Max Act: 0.9557. Min Act: -0.0000

Data Index: 1661040 (The Pile)

Max Activating Token Index: 930

Text #9

Max Range: 1.3262. Min Range: -1.3262

Max Act: 1.0721. Min Act: -0.0000

Data Index: 946831 (The Pile)

Max Activating Token Index: 804

Text #10

Max Range: 1.3262. Min Range: -1.3262

Max Act: 0.9169. Min Act: -0.0000

Data Index: 1842714 (The Pile)

Max Activating Token Index: 724

Text #11

Max Range: 1.3262. Min Range: -1.3262

Max Act: 0.8770. Min Act: -0.0000

Data Index: 60787 (The Pile)

Max Activating Token Index: 350

Text #12

Max Range: 1.3262. Min Range: -1.3262

Max Act: 0.8953. Min Act: -0.0000

Data Index: 1427571 (The Pile)

Max Activating Token Index: 790

Text #13

Max Range: 1.3262. Min Range: -1.3262

Max Act: 0.9077. Min Act: -0.0000

Data Index: 456710 (The Pile)

Max Activating Token Index: 517

Text #14

Max Range: 1.3262. Min Range: -1.3262

Max Act: 0.8556. Min Act: -0.0000

Data Index: 278073 (The Pile)

Max Activating Token Index: 227

Text #15

Max Range: 1.3262. Min Range: -1.3262

Max Act: 0.7914. Min Act: -0.0000

Data Index: 439491 (The Pile)

Max Activating Token Index: 540

Text #16

Max Range: 1.3262. Min Range: -1.3262

Max Act: 0.8094. Min Act: -0.0000

Data Index: 245348 (The Pile)

Max Activating Token Index: 185

Text #17

Max Range: 1.3262. Min Range: -1.3262

Max Act: 0.9159. Min Act: -0.0000

Data Index: 572462 (The Pile)

Max Activating Token Index: 605

Text #18

Max Range: 1.3262. Min Range: -1.3262

Max Act: 0.8927. Min Act: -0.0000

Data Index: 1603857 (The Pile)

Max Activating Token Index: 743

Text #19

Max Range: 1.3262. Min Range: -1.3262

Max Act: 0.7198. Min Act: -0.0000

Data Index: 1676359 (The Pile)

Max Activating Token Index: 197