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

Dataset: The Pile

Neuron 3949 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 7.8839. Min Range: -7.8839

Max Act: 6.9225. Min Act: -0.0000

Data Index: 182433 (The Pile)

Max Activating Token Index: 631

Text #1

Max Range: 7.8839. Min Range: -7.8839

Max Act: 7.8839. Min Act: -0.0000

Data Index: 1285659 (The Pile)

Max Activating Token Index: 427

Text #2

Max Range: 7.8839. Min Range: -7.8839

Max Act: 7.4160. Min Act: -0.0000

Data Index: 1008307 (The Pile)

Max Activating Token Index: 711

Text #3

Max Range: 7.8839. Min Range: -7.8839

Max Act: 7.2961. Min Act: -0.0000

Data Index: 968074 (The Pile)

Max Activating Token Index: 539

Text #4

Max Range: 7.8839. Min Range: -7.8839

Max Act: 6.5278. Min Act: -0.0000

Data Index: 1997611 (The Pile)

Max Activating Token Index: 137

Text #5

Max Range: 7.8839. Min Range: -7.8839

Max Act: 6.9082. Min Act: -0.0000

Data Index: 724730 (The Pile)

Max Activating Token Index: 228

Text #6

Max Range: 7.8839. Min Range: -7.8839

Max Act: 6.6752. Min Act: -0.0000

Data Index: 220231 (The Pile)

Max Activating Token Index: 763

Text #7

Max Range: 7.8839. Min Range: -7.8839

Max Act: 7.4982. Min Act: -0.0000

Data Index: 1091006 (The Pile)

Max Activating Token Index: 134

Text #8

Max Range: 7.8839. Min Range: -7.8839

Max Act: 7.1431. Min Act: -0.0000

Data Index: 1199942 (The Pile)

Max Activating Token Index: 473

Text #9

Max Range: 7.8839. Min Range: -7.8839

Max Act: 7.2510. Min Act: -0.0000

Data Index: 1320725 (The Pile)

Max Activating Token Index: 766

Text #10

Max Range: 7.8839. Min Range: -7.8839

Max Act: 6.4970. Min Act: -0.0000

Data Index: 137802 (The Pile)

Max Activating Token Index: 311

Text #11

Max Range: 7.8839. Min Range: -7.8839

Max Act: 6.5737. Min Act: -0.0000

Data Index: 650970 (The Pile)

Max Activating Token Index: 967

Text #12

Max Range: 7.8839. Min Range: -7.8839

Max Act: 7.1223. Min Act: -0.0000

Data Index: 1061465 (The Pile)

Max Activating Token Index: 654

Text #13

Max Range: 7.8839. Min Range: -7.8839

Max Act: 6.8987. Min Act: -0.0000

Data Index: 434894 (The Pile)

Max Activating Token Index: 646

Text #14

Max Range: 7.8839. Min Range: -7.8839

Max Act: 6.5520. Min Act: -0.0000

Data Index: 1510752 (The Pile)

Max Activating Token Index: 513

Text #15

Max Range: 7.8839. Min Range: -7.8839

Max Act: 6.6569. Min Act: -0.0000

Data Index: 598814 (The Pile)

Max Activating Token Index: 629

Text #16

Max Range: 7.8839. Min Range: -7.8839

Max Act: 6.7924. Min Act: -0.0000

Data Index: 243609 (The Pile)

Max Activating Token Index: 856

Text #17

Max Range: 7.8839. Min Range: -7.8839

Max Act: 6.1318. Min Act: -0.0000

Data Index: 1560323 (The Pile)

Max Activating Token Index: 101

Text #18

Max Range: 7.8839. Min Range: -7.8839

Max Act: 6.4759. Min Act: -0.0000

Data Index: 34921 (The Pile)

Max Activating Token Index: 789

Text #19

Max Range: 7.8839. Min Range: -7.8839

Max Act: 6.4696. Min Act: -0.0000

Data Index: 1129901 (The Pile)

Max Activating Token Index: 92