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

Dataset: The Pile

Neuron 1995 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: 0.5772. Min Range: -0.5772

Max Act: 0.5692. Min Act: -0.0000

Data Index: 805571 (The Pile)

Max Activating Token Index: 517

Text #1

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.4799. Min Act: -0.0000

Data Index: 715662 (The Pile)

Max Activating Token Index: 1001

Text #2

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.5393. Min Act: -0.0000

Data Index: 343093 (The Pile)

Max Activating Token Index: 32

Text #3

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.5772. Min Act: -0.0000

Data Index: 907574 (The Pile)

Max Activating Token Index: 941

Text #4

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.4483. Min Act: -0.0000

Data Index: 1793021 (The Pile)

Max Activating Token Index: 316

Text #5

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.5179. Min Act: -0.0000

Data Index: 704503 (The Pile)

Max Activating Token Index: 133

Text #6

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.4589. Min Act: -0.0000

Data Index: 839692 (The Pile)

Max Activating Token Index: 301

Text #7

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.4488. Min Act: -0.0000

Data Index: 1842169 (The Pile)

Max Activating Token Index: 469

Text #8

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.4669. Min Act: -0.0000

Data Index: 1529812 (The Pile)

Max Activating Token Index: 530

Text #9

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.4865. Min Act: -0.0000

Data Index: 1222237 (The Pile)

Max Activating Token Index: 963

Text #10

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.4363. Min Act: -0.0000

Data Index: 338087 (The Pile)

Max Activating Token Index: 991

Text #11

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.4114. Min Act: -0.0000

Data Index: 1197658 (The Pile)

Max Activating Token Index: 886

Text #12

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.4295. Min Act: -0.0000

Data Index: 478857 (The Pile)

Max Activating Token Index: 37

Text #13

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.4304. Min Act: -0.0000

Data Index: 1420022 (The Pile)

Max Activating Token Index: 239

Text #14

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.4037. Min Act: -0.0000

Data Index: 1153863 (The Pile)

Max Activating Token Index: 959

Text #15

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.4204. Min Act: -0.0000

Data Index: 711310 (The Pile)

Max Activating Token Index: 30

Text #16

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.3849. Min Act: -0.0000

Data Index: 358193 (The Pile)

Max Activating Token Index: 788

Text #17

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.4038. Min Act: -0.0000

Data Index: 1657563 (The Pile)

Max Activating Token Index: 516

Text #18

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.3461. Min Act: -0.0000

Data Index: 567674 (The Pile)

Max Activating Token Index: 774

Text #19

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.3981. Min Act: -0.0000

Data Index: 1191883 (The Pile)

Max Activating Token Index: 670