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

Dataset: The Pile

Neuron 1252 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.5211. Min Act: -0.0000

Data Index: 1196023 (The Pile)

Max Activating Token Index: 898

Text #1

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.3941. Min Act: -0.0000

Data Index: 908222 (The Pile)

Max Activating Token Index: 722

Text #2

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.3583. Min Act: -0.0000

Data Index: 1861138 (The Pile)

Max Activating Token Index: 309

Text #3

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.3828. Min Act: -0.0000

Data Index: 440453 (The Pile)

Max Activating Token Index: 115

Text #4

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.3493. Min Act: -0.0000

Data Index: 1473560 (The Pile)

Max Activating Token Index: 9

Text #5

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.3789. Min Act: -0.0000

Data Index: 597052 (The Pile)

Max Activating Token Index: 35

Text #6

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.3515. Min Act: -0.0000

Data Index: 1099169 (The Pile)

Max Activating Token Index: 327

Text #7

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.3531. Min Act: -0.0000

Data Index: 1467804 (The Pile)

Max Activating Token Index: 818

Text #8

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.3389. Min Act: -0.0000

Data Index: 669706 (The Pile)

Max Activating Token Index: 51

Text #9

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.3423. Min Act: -0.0000

Data Index: 852065 (The Pile)

Max Activating Token Index: 626

Text #10

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.3490. Min Act: -0.0000

Data Index: 789163 (The Pile)

Max Activating Token Index: 944

Text #11

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.3701. Min Act: -0.0000

Data Index: 1531901 (The Pile)

Max Activating Token Index: 918

Text #12

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.3284. Min Act: -0.0000

Data Index: 895920 (The Pile)

Max Activating Token Index: 798

Text #13

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.3454. Min Act: -0.0000

Data Index: 136794 (The Pile)

Max Activating Token Index: 33

Text #14

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.3452. Min Act: -0.0000

Data Index: 869619 (The Pile)

Max Activating Token Index: 896

Text #15

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.3269. Min Act: -0.0000

Data Index: 1213034 (The Pile)

Max Activating Token Index: 369

Text #16

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.3415. Min Act: -0.0000

Data Index: 640221 (The Pile)

Max Activating Token Index: 1017

Text #17

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.3371. Min Act: -0.0000

Data Index: 1762606 (The Pile)

Max Activating Token Index: 256

Text #18

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.3280. Min Act: -0.0000

Data Index: 1782542 (The Pile)

Max Activating Token Index: 16

Text #19

Max Range: 0.5211. Min Range: -0.5211

Max Act: 0.3287. Min Act: -0.0000

Data Index: 1996538 (The Pile)

Max Activating Token Index: 808