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

Dataset: The Pile

Neuron 2313 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: 0.4903. Min Range: -0.4903

Max Act: 0.4903. Min Act: -0.0000

Data Index: 1613810 (The Pile)

Max Activating Token Index: 192

Text #1

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.4821. Min Act: -0.0000

Data Index: 1664304 (The Pile)

Max Activating Token Index: 363

Text #2

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.4095. Min Act: -0.0000

Data Index: 310939 (The Pile)

Max Activating Token Index: 280

Text #3

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.4457. Min Act: -0.0000

Data Index: 292848 (The Pile)

Max Activating Token Index: 862

Text #4

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.4229. Min Act: -0.0000

Data Index: 1070375 (The Pile)

Max Activating Token Index: 432

Text #5

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.3836. Min Act: -0.0000

Data Index: 652509 (The Pile)

Max Activating Token Index: 993

Text #6

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.3875. Min Act: -0.0000

Data Index: 1055778 (The Pile)

Max Activating Token Index: 714

Text #7

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.3624. Min Act: -0.0000

Data Index: 1410751 (The Pile)

Max Activating Token Index: 259

Text #8

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.4280. Min Act: -0.0000

Data Index: 1270246 (The Pile)

Max Activating Token Index: 393

Text #9

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.3623. Min Act: -0.0000

Data Index: 1772619 (The Pile)

Max Activating Token Index: 503

Text #10

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.3704. Min Act: -0.0000

Data Index: 204976 (The Pile)

Max Activating Token Index: 367

Text #11

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.3702. Min Act: -0.0000

Data Index: 12932 (The Pile)

Max Activating Token Index: 294

Text #12

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.3796. Min Act: -0.0000

Data Index: 315696 (The Pile)

Max Activating Token Index: 428

Text #13

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.3152. Min Act: -0.0000

Data Index: 1408747 (The Pile)

Max Activating Token Index: 382

Text #14

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.3677. Min Act: -0.0000

Data Index: 654733 (The Pile)

Max Activating Token Index: 314

Text #15

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.3740. Min Act: -0.0000

Data Index: 280159 (The Pile)

Max Activating Token Index: 520

Text #16

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.3682. Min Act: -0.0000

Data Index: 989485 (The Pile)

Max Activating Token Index: 243

Text #17

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.3670. Min Act: -0.0000

Data Index: 1162248 (The Pile)

Max Activating Token Index: 776

Text #18

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.3486. Min Act: -0.0000

Data Index: 1863446 (The Pile)

Max Activating Token Index: 578

Text #19

Max Range: 0.4903. Min Range: -0.4903

Max Act: 0.3464. Min Act: -0.0000

Data Index: 962554 (The Pile)

Max Activating Token Index: 703