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

Dataset: The Pile

Neuron 3327 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: 0.3797. Min Range: -0.3797

Max Act: 0.3797. Min Act: -0.0000

Data Index: 734060 (The Pile)

Max Activating Token Index: 658

Text #1

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.3327. Min Act: -0.0000

Data Index: 433395 (The Pile)

Max Activating Token Index: 981

Text #2

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.3261. Min Act: -0.0000

Data Index: 765793 (The Pile)

Max Activating Token Index: 610

Text #3

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.3133. Min Act: -0.0000

Data Index: 1062037 (The Pile)

Max Activating Token Index: 425

Text #4

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.3214. Min Act: -0.0000

Data Index: 1528710 (The Pile)

Max Activating Token Index: 228

Text #5

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.3072. Min Act: -0.0000

Data Index: 833236 (The Pile)

Max Activating Token Index: 292

Text #6

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.3185. Min Act: -0.0000

Data Index: 1515758 (The Pile)

Max Activating Token Index: 969

Text #7

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.3041. Min Act: -0.0000

Data Index: 826716 (The Pile)

Max Activating Token Index: 137

Text #8

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.3129. Min Act: -0.0000

Data Index: 1931208 (The Pile)

Max Activating Token Index: 500

Text #9

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.3090. Min Act: -0.0000

Data Index: 538232 (The Pile)

Max Activating Token Index: 438

Text #10

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.3044. Min Act: -0.0000

Data Index: 159768 (The Pile)

Max Activating Token Index: 236

Text #11

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.2756. Min Act: -0.0000

Data Index: 1647762 (The Pile)

Max Activating Token Index: 420

Text #12

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.2852. Min Act: -0.0000

Data Index: 975315 (The Pile)

Max Activating Token Index: 100

Text #13

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.2911. Min Act: -0.0000

Data Index: 216118 (The Pile)

Max Activating Token Index: 85

Text #14

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.2876. Min Act: -0.0000

Data Index: 1877025 (The Pile)

Max Activating Token Index: 428

Text #15

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.2873. Min Act: -0.0000

Data Index: 136609 (The Pile)

Max Activating Token Index: 324

Text #16

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.2696. Min Act: -0.0000

Data Index: 1559342 (The Pile)

Max Activating Token Index: 375

Text #17

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.2666. Min Act: -0.0000

Data Index: 1092935 (The Pile)

Max Activating Token Index: 675

Text #18

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.2745. Min Act: -0.0000

Data Index: 11942 (The Pile)

Max Activating Token Index: 937

Text #19

Max Range: 0.3797. Min Range: -0.3797

Max Act: 0.2828. Min Act: -0.0000

Data Index: 1938366 (The Pile)

Max Activating Token Index: 759