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

Dataset: The Pile

Neuron 2122 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: 5.2762. Min Range: -5.2762

Max Act: 5.2762. Min Act: -0.0000

Data Index: 1890627 (The Pile)

Max Activating Token Index: 177

Text #1

Max Range: 5.2762. Min Range: -5.2762

Max Act: 4.8880. Min Act: -0.0000

Data Index: 1163120 (The Pile)

Max Activating Token Index: 690

Text #2

Max Range: 5.2762. Min Range: -5.2762

Max Act: 4.9675. Min Act: -0.0000

Data Index: 594924 (The Pile)

Max Activating Token Index: 449

Text #3

Max Range: 5.2762. Min Range: -5.2762

Max Act: 5.0437. Min Act: -0.0000

Data Index: 668608 (The Pile)

Max Activating Token Index: 926

Text #4

Max Range: 5.2762. Min Range: -5.2762

Max Act: 3.8913. Min Act: -0.0000

Data Index: 1790029 (The Pile)

Max Activating Token Index: 847

Text #5

Max Range: 5.2762. Min Range: -5.2762

Max Act: 4.2408. Min Act: -0.0000

Data Index: 1113793 (The Pile)

Max Activating Token Index: 66

Text #6

Max Range: 5.2762. Min Range: -5.2762

Max Act: 3.5170. Min Act: -0.0000

Data Index: 1416962 (The Pile)

Max Activating Token Index: 623

Text #7

Max Range: 5.2762. Min Range: -5.2762

Max Act: 4.3956. Min Act: -0.0000

Data Index: 1453060 (The Pile)

Max Activating Token Index: 756

Text #8

Max Range: 5.2762. Min Range: -5.2762

Max Act: 4.2891. Min Act: -0.0000

Data Index: 432130 (The Pile)

Max Activating Token Index: 761

Text #9

Max Range: 5.2762. Min Range: -5.2762

Max Act: 3.6474. Min Act: -0.0000

Data Index: 122405 (The Pile)

Max Activating Token Index: 815

Text #10

Max Range: 5.2762. Min Range: -5.2762

Max Act: 3.4971. Min Act: -0.0000

Data Index: 1543802 (The Pile)

Max Activating Token Index: 865

Text #11

Max Range: 5.2762. Min Range: -5.2762

Max Act: 3.9566. Min Act: -0.0000

Data Index: 1439329 (The Pile)

Max Activating Token Index: 812

Text #12

Max Range: 5.2762. Min Range: -5.2762

Max Act: 3.4086. Min Act: -0.0000

Data Index: 1557431 (The Pile)

Max Activating Token Index: 917

Text #13

Max Range: 5.2762. Min Range: -5.2762

Max Act: 3.2613. Min Act: -0.0000

Data Index: 1725244 (The Pile)

Max Activating Token Index: 651

Text #14

Max Range: 5.2762. Min Range: -5.2762

Max Act: 3.5336. Min Act: -0.0000

Data Index: 1695966 (The Pile)

Max Activating Token Index: 157

Text #15

Max Range: 5.2762. Min Range: -5.2762

Max Act: 3.8795. Min Act: -0.0000

Data Index: 1134116 (The Pile)

Max Activating Token Index: 578

Text #16

Max Range: 5.2762. Min Range: -5.2762

Max Act: 3.6534. Min Act: -0.0000

Data Index: 1156406 (The Pile)

Max Activating Token Index: 551

Text #17

Max Range: 5.2762. Min Range: -5.2762

Max Act: 4.6593. Min Act: -0.0000

Data Index: 741281 (The Pile)

Max Activating Token Index: 751

Text #18

Max Range: 5.2762. Min Range: -5.2762

Max Act: 4.0332. Min Act: -0.0000

Data Index: 252147 (The Pile)

Max Activating Token Index: 961

Text #19

Max Range: 5.2762. Min Range: -5.2762

Max Act: 3.5938. Min Act: -0.0000

Data Index: 603455 (The Pile)

Max Activating Token Index: 783