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

Dataset: The Pile

Neuron 3269 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: 0.4731. Min Range: -0.4731

Max Act: 0.4731. Min Act: -0.0000

Data Index: 343155 (The Pile)

Max Activating Token Index: 791

Text #1

Max Range: 0.4731. Min Range: -0.4731

Max Act: 0.4522. Min Act: -0.0000

Data Index: 1701695 (The Pile)

Max Activating Token Index: 376

Text #2

Max Range: 0.4731. Min Range: -0.4731

Max Act: 0.4059. Min Act: -0.0000

Data Index: 1228033 (The Pile)

Max Activating Token Index: 70

Text #3

Max Range: 0.4731. Min Range: -0.4731

Max Act: 0.4032. Min Act: -0.0000

Data Index: 622976 (The Pile)

Max Activating Token Index: 66

Text #4

Max Range: 0.4731. Min Range: -0.4731

Max Act: 0.4055. Min Act: -0.0000

Data Index: 1476977 (The Pile)

Max Activating Token Index: 918

Text #5

Max Range: 0.4731. Min Range: -0.4731

Max Act: 0.3450. Min Act: -0.0000

Data Index: 190823 (The Pile)

Max Activating Token Index: 736

Text #6

Max Range: 0.4731. Min Range: -0.4731

Max Act: 0.3874. Min Act: -0.0000

Data Index: 44021 (The Pile)

Max Activating Token Index: 808

Text #7

Max Range: 0.4731. Min Range: -0.4731

Max Act: 0.3734. Min Act: -0.0000

Data Index: 1156659 (The Pile)

Max Activating Token Index: 875

Text #8

Max Range: 0.4731. Min Range: -0.4731

Max Act: 0.3825. Min Act: -0.0000

Data Index: 220487 (The Pile)

Max Activating Token Index: 280

Text #9

Max Range: 0.4731. Min Range: -0.4731

Max Act: 0.3795. Min Act: -0.0000

Data Index: 310618 (The Pile)

Max Activating Token Index: 753

Text #10

Max Range: 0.4731. Min Range: -0.4731

Max Act: 0.3294. Min Act: -0.0000

Data Index: 380052 (The Pile)

Max Activating Token Index: 645

Text #11

Max Range: 0.4731. Min Range: -0.4731

Max Act: 0.3566. Min Act: -0.0000

Data Index: 1320967 (The Pile)

Max Activating Token Index: 896

Text #12

Max Range: 0.4731. Min Range: -0.4731

Max Act: 0.3774. Min Act: -0.0000

Data Index: 806705 (The Pile)

Max Activating Token Index: 922

Text #13

Max Range: 0.4731. Min Range: -0.4731

Max Act: 0.3350. Min Act: -0.0000

Data Index: 1086628 (The Pile)

Max Activating Token Index: 313

Text #14

Max Range: 0.4731. Min Range: -0.4731

Max Act: 0.3964. Min Act: -0.0000

Data Index: 468002 (The Pile)

Max Activating Token Index: 768

Text #15

Max Range: 0.4731. Min Range: -0.4731

Max Act: 0.4002. Min Act: -0.0000

Data Index: 1690417 (The Pile)

Max Activating Token Index: 192

Text #16

Max Range: 0.4731. Min Range: -0.4731

Max Act: 0.3478. Min Act: -0.0000

Data Index: 858486 (The Pile)

Max Activating Token Index: 154

Text #17

Max Range: 0.4731. Min Range: -0.4731

Max Act: 0.3412. Min Act: -0.0000

Data Index: 195863 (The Pile)

Max Activating Token Index: 170

Text #18

Max Range: 0.4731. Min Range: -0.4731

Max Act: 0.3395. Min Act: -0.0000

Data Index: 1751584 (The Pile)

Max Activating Token Index: 733

Text #19

Max Range: 0.4731. Min Range: -0.4731

Max Act: 0.3361. Min Act: -0.0000

Data Index: 1047251 (The Pile)

Max Activating Token Index: 157