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

Dataset: The Pile

Neuron 4727 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5449. Min Range: -0.5449

Max Act: 0.5449. Min Act: -0.0000

Data Index: 1559699 (The Pile)

Max Activating Token Index: 111

Text #1

Max Range: 0.5449. Min Range: -0.5449

Max Act: 0.5059. Min Act: -0.0000

Data Index: 295168 (The Pile)

Max Activating Token Index: 96

Text #2

Max Range: 0.5449. Min Range: -0.5449

Max Act: 0.4434. Min Act: -0.0000

Data Index: 1758015 (The Pile)

Max Activating Token Index: 491

Text #3

Max Range: 0.5449. Min Range: -0.5449

Max Act: 0.3310. Min Act: -0.0000

Data Index: 375894 (The Pile)

Max Activating Token Index: 912

Text #4

Max Range: 0.5449. Min Range: -0.5449

Max Act: 0.4002. Min Act: -0.0000

Data Index: 2695 (The Pile)

Max Activating Token Index: 939

Text #5

Max Range: 0.5449. Min Range: -0.5449

Max Act: 0.3994. Min Act: -0.0000

Data Index: 321686 (The Pile)

Max Activating Token Index: 650

Text #6

Max Range: 0.5449. Min Range: -0.5449

Max Act: 0.4091. Min Act: -0.0000

Data Index: 801735 (The Pile)

Max Activating Token Index: 362

Text #7

Max Range: 0.5449. Min Range: -0.5449

Max Act: 0.3709. Min Act: -0.0000

Data Index: 151894 (The Pile)

Max Activating Token Index: 370

Text #8

Max Range: 0.5449. Min Range: -0.5449

Max Act: 0.3533. Min Act: -0.0000

Data Index: 370539 (The Pile)

Max Activating Token Index: 525

Text #9

Max Range: 0.5449. Min Range: -0.5449

Max Act: 0.3672. Min Act: -0.0000

Data Index: 1258550 (The Pile)

Max Activating Token Index: 55

Text #10

Max Range: 0.5449. Min Range: -0.5449

Max Act: 0.3665. Min Act: -0.0000

Data Index: 1852136 (The Pile)

Max Activating Token Index: 855

Text #11

Max Range: 0.5449. Min Range: -0.5449

Max Act: 0.3994. Min Act: -0.0000

Data Index: 1743328 (The Pile)

Max Activating Token Index: 395

Text #12

Max Range: 0.5449. Min Range: -0.5449

Max Act: 0.3502. Min Act: -0.0000

Data Index: 90591 (The Pile)

Max Activating Token Index: 466

Text #13

Max Range: 0.5449. Min Range: -0.5449

Max Act: 0.3310. Min Act: -0.0000

Data Index: 1090939 (The Pile)

Max Activating Token Index: 606

Text #14

Max Range: 0.5449. Min Range: -0.5449

Max Act: 0.3680. Min Act: -0.0000

Data Index: 1422773 (The Pile)

Max Activating Token Index: 92

Text #15

Max Range: 0.5449. Min Range: -0.5449

Max Act: 0.3615. Min Act: -0.0000

Data Index: 442467 (The Pile)

Max Activating Token Index: 290

Text #16

Max Range: 0.5449. Min Range: -0.5449

Max Act: 0.3822. Min Act: -0.0000

Data Index: 62778 (The Pile)

Max Activating Token Index: 747

Text #17

Max Range: 0.5449. Min Range: -0.5449

Max Act: 0.3349. Min Act: -0.0000

Data Index: 1992227 (The Pile)

Max Activating Token Index: 881

Text #18

Max Range: 0.5449. Min Range: -0.5449

Max Act: 0.3314. Min Act: -0.0000

Data Index: 618867 (The Pile)

Max Activating Token Index: 348

Text #19

Max Range: 0.5449. Min Range: -0.5449

Max Act: 0.3026. Min Act: -0.0000

Data Index: 1087446 (The Pile)

Max Activating Token Index: 199