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

Dataset: The Pile

Neuron 1618 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5294. Min Range: -0.5294

Max Act: 0.5294. Min Act: -0.0000

Data Index: 1999540 (The Pile)

Max Activating Token Index: 580

Text #1

Max Range: 0.5294. Min Range: -0.5294

Max Act: 0.4740. Min Act: -0.0000

Data Index: 556664 (The Pile)

Max Activating Token Index: 650

Text #2

Max Range: 0.5294. Min Range: -0.5294

Max Act: 0.4051. Min Act: -0.0000

Data Index: 1760378 (The Pile)

Max Activating Token Index: 165

Text #3

Max Range: 0.5294. Min Range: -0.5294

Max Act: 0.3510. Min Act: -0.0000

Data Index: 452943 (The Pile)

Max Activating Token Index: 199

Text #4

Max Range: 0.5294. Min Range: -0.5294

Max Act: 0.3928. Min Act: -0.0000

Data Index: 1921942 (The Pile)

Max Activating Token Index: 913

Text #5

Max Range: 0.5294. Min Range: -0.5294

Max Act: 0.4112. Min Act: -0.0000

Data Index: 1827654 (The Pile)

Max Activating Token Index: 99

Text #6

Max Range: 0.5294. Min Range: -0.5294

Max Act: 0.3845. Min Act: -0.0000

Data Index: 1076911 (The Pile)

Max Activating Token Index: 409

Text #7

Max Range: 0.5294. Min Range: -0.5294

Max Act: 0.3581. Min Act: -0.0000

Data Index: 578876 (The Pile)

Max Activating Token Index: 944

Text #8

Max Range: 0.5294. Min Range: -0.5294

Max Act: 0.3722. Min Act: -0.0000

Data Index: 1008974 (The Pile)

Max Activating Token Index: 569

Text #9

Max Range: 0.5294. Min Range: -0.5294

Max Act: 0.3720. Min Act: -0.0000

Data Index: 1596542 (The Pile)

Max Activating Token Index: 635

Text #10

Max Range: 0.5294. Min Range: -0.5294

Max Act: 0.3640. Min Act: -0.0000

Data Index: 266211 (The Pile)

Max Activating Token Index: 216

Text #11

Max Range: 0.5294. Min Range: -0.5294

Max Act: 0.3759. Min Act: -0.0000

Data Index: 617730 (The Pile)

Max Activating Token Index: 307

Text #12

Max Range: 0.5294. Min Range: -0.5294

Max Act: 0.3616. Min Act: -0.0000

Data Index: 53488 (The Pile)

Max Activating Token Index: 104

Text #13

Max Range: 0.5294. Min Range: -0.5294

Max Act: 0.3378. Min Act: -0.0000

Data Index: 1917822 (The Pile)

Max Activating Token Index: 218

Text #14

Max Range: 0.5294. Min Range: -0.5294

Max Act: 0.3528. Min Act: -0.0000

Data Index: 343048 (The Pile)

Max Activating Token Index: 268

Text #15

Max Range: 0.5294. Min Range: -0.5294

Max Act: 0.3494. Min Act: -0.0000

Data Index: 1963824 (The Pile)

Max Activating Token Index: 270

Text #16

Max Range: 0.5294. Min Range: -0.5294

Max Act: 0.3263. Min Act: -0.0000

Data Index: 297096 (The Pile)

Max Activating Token Index: 256

Text #17

Max Range: 0.5294. Min Range: -0.5294

Max Act: 0.3423. Min Act: -0.0000

Data Index: 1826055 (The Pile)

Max Activating Token Index: 482

Text #18

Max Range: 0.5294. Min Range: -0.5294

Max Act: 0.3420. Min Act: -0.0000

Data Index: 79183 (The Pile)

Max Activating Token Index: 400

Text #19

Max Range: 0.5294. Min Range: -0.5294

Max Act: 0.3320. Min Act: -0.0000

Data Index: 715106 (The Pile)

Max Activating Token Index: 347