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

Dataset: The Pile

Neuron 3717 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0794. Min Act: 0.0000

Data Index: 950712 (The Pile)

Max Activating Token Index: 21

Text #1

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0610. Min Act: 0.0000

Data Index: 712176 (The Pile)

Max Activating Token Index: 9

Text #2

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0544. Min Act: -0.0000

Data Index: 864923 (The Pile)

Max Activating Token Index: 9

Text #3

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0512. Min Act: -0.0000

Data Index: 442938 (The Pile)

Max Activating Token Index: 21

Text #4

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0508. Min Act: -0.0000

Data Index: 1902383 (The Pile)

Max Activating Token Index: 5

Text #5

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0489. Min Act: 0.0000

Data Index: 921707 (The Pile)

Max Activating Token Index: 15

Text #6

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0505. Min Act: -0.0000

Data Index: 630544 (The Pile)

Max Activating Token Index: 23

Text #7

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0506. Min Act: 0.0000

Data Index: 59449 (The Pile)

Max Activating Token Index: 35

Text #8

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0497. Min Act: 0.0000

Data Index: 1682519 (The Pile)

Max Activating Token Index: 55

Text #9

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0492. Min Act: 0.0000

Data Index: 1482210 (The Pile)

Max Activating Token Index: 21

Text #10

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0485. Min Act: 0.0000

Data Index: 473631 (The Pile)

Max Activating Token Index: 12

Text #11

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0496. Min Act: -0.0000

Data Index: 282710 (The Pile)

Max Activating Token Index: 63

Text #12

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0472. Min Act: 0.0000

Data Index: 959744 (The Pile)

Max Activating Token Index: 27

Text #13

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0473. Min Act: -0.0000

Data Index: 1212585 (The Pile)

Max Activating Token Index: 14

Text #14

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0463. Min Act: 0.0000

Data Index: 457628 (The Pile)

Max Activating Token Index: 28

Text #15

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0461. Min Act: 0.0000

Data Index: 1230040 (The Pile)

Max Activating Token Index: 4

Text #16

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0453. Min Act: 0.0000

Data Index: 1580599 (The Pile)

Max Activating Token Index: 12

Text #17

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0448. Min Act: -0.0000

Data Index: 1081951 (The Pile)

Max Activating Token Index: 25

Text #18

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0445. Min Act: -0.0000

Data Index: 1986653 (The Pile)

Max Activating Token Index: 8

Text #19

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0443. Min Act: 0.0000

Data Index: 122323 (The Pile)

Max Activating Token Index: 31