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

Dataset: The Pile

Neuron 501 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8899. Min Range: -1.8899

Max Act: 1.8899. Min Act: -0.0000

Data Index: 647967 (The Pile)

Max Activating Token Index: 117

Text #1

Max Range: 1.8899. Min Range: -1.8899

Max Act: 1.6753. Min Act: -0.0000

Data Index: 531787 (The Pile)

Max Activating Token Index: 808

Text #2

Max Range: 1.8899. Min Range: -1.8899

Max Act: 1.6369. Min Act: -0.0000

Data Index: 1905487 (The Pile)

Max Activating Token Index: 344

Text #3

Max Range: 1.8899. Min Range: -1.8899

Max Act: 1.5759. Min Act: -0.0000

Data Index: 545014 (The Pile)

Max Activating Token Index: 394

Text #4

Max Range: 1.8899. Min Range: -1.8899

Max Act: 1.7177. Min Act: -0.0000

Data Index: 283207 (The Pile)

Max Activating Token Index: 239

Text #5

Max Range: 1.8899. Min Range: -1.8899

Max Act: 1.4394. Min Act: -0.0000

Data Index: 1314114 (The Pile)

Max Activating Token Index: 289

Text #6

Max Range: 1.8899. Min Range: -1.8899

Max Act: 1.5395. Min Act: -0.0000

Data Index: 988315 (The Pile)

Max Activating Token Index: 486

Text #7

Max Range: 1.8899. Min Range: -1.8899

Max Act: 1.3611. Min Act: -0.0000

Data Index: 873260 (The Pile)

Max Activating Token Index: 719

Text #8

Max Range: 1.8899. Min Range: -1.8899

Max Act: 1.6198. Min Act: -0.0000

Data Index: 775036 (The Pile)

Max Activating Token Index: 817

Text #9

Max Range: 1.8899. Min Range: -1.8899

Max Act: 1.4472. Min Act: -0.0000

Data Index: 1679999 (The Pile)

Max Activating Token Index: 658

Text #10

Max Range: 1.8899. Min Range: -1.8899

Max Act: 1.4601. Min Act: -0.0000

Data Index: 1901178 (The Pile)

Max Activating Token Index: 712

Text #11

Max Range: 1.8899. Min Range: -1.8899

Max Act: 1.2912. Min Act: -0.0000

Data Index: 288958 (The Pile)

Max Activating Token Index: 996

Text #12

Max Range: 1.8899. Min Range: -1.8899

Max Act: 1.3496. Min Act: -0.0000

Data Index: 1761838 (The Pile)

Max Activating Token Index: 898

Text #13

Max Range: 1.8899. Min Range: -1.8899

Max Act: 1.2892. Min Act: -0.0000

Data Index: 854029 (The Pile)

Max Activating Token Index: 70

Text #14

Max Range: 1.8899. Min Range: -1.8899

Max Act: 1.4567. Min Act: -0.0000

Data Index: 68162 (The Pile)

Max Activating Token Index: 375

Text #15

Max Range: 1.8899. Min Range: -1.8899

Max Act: 1.3553. Min Act: -0.0000

Data Index: 246626 (The Pile)

Max Activating Token Index: 957

Text #16

Max Range: 1.8899. Min Range: -1.8899

Max Act: 1.4280. Min Act: -0.0000

Data Index: 1620053 (The Pile)

Max Activating Token Index: 94

Text #17

Max Range: 1.8899. Min Range: -1.8899

Max Act: 1.3301. Min Act: -0.0000

Data Index: 40283 (The Pile)

Max Activating Token Index: 974

Text #18

Max Range: 1.8899. Min Range: -1.8899

Max Act: 1.3844. Min Act: -0.0000

Data Index: 1064730 (The Pile)

Max Activating Token Index: 935

Text #19

Max Range: 1.8899. Min Range: -1.8899

Max Act: 1.1905. Min Act: -0.0000

Data Index: 944788 (The Pile)

Max Activating Token Index: 1019