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

Dataset: The Pile

Neuron 2555 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: 0.4507. Min Range: -0.4507

Max Act: 0.4431. Min Act: -0.0000

Data Index: 1601945 (The Pile)

Max Activating Token Index: 822

Text #1

Max Range: 0.4507. Min Range: -0.4507

Max Act: 0.4507. Min Act: -0.0000

Data Index: 347788 (The Pile)

Max Activating Token Index: 1010

Text #2

Max Range: 0.4507. Min Range: -0.4507

Max Act: 0.4360. Min Act: -0.0000

Data Index: 1527027 (The Pile)

Max Activating Token Index: 664

Text #3

Max Range: 0.4507. Min Range: -0.4507

Max Act: 0.3822. Min Act: -0.0000

Data Index: 424260 (The Pile)

Max Activating Token Index: 957

Text #4

Max Range: 0.4507. Min Range: -0.4507

Max Act: 0.3777. Min Act: -0.0000

Data Index: 1655532 (The Pile)

Max Activating Token Index: 514

Text #5

Max Range: 0.4507. Min Range: -0.4507

Max Act: 0.3716. Min Act: -0.0000

Data Index: 1067011 (The Pile)

Max Activating Token Index: 415

Text #6

Max Range: 0.4507. Min Range: -0.4507

Max Act: 0.3817. Min Act: -0.0000

Data Index: 1888822 (The Pile)

Max Activating Token Index: 928

Text #7

Max Range: 0.4507. Min Range: -0.4507

Max Act: 0.3486. Min Act: -0.0000

Data Index: 1637766 (The Pile)

Max Activating Token Index: 1018

Text #8

Max Range: 0.4507. Min Range: -0.4507

Max Act: 0.3865. Min Act: -0.0000

Data Index: 706363 (The Pile)

Max Activating Token Index: 60

Text #9

Max Range: 0.4507. Min Range: -0.4507

Max Act: 0.3351. Min Act: 0.0000

Data Index: 464194 (The Pile)

Max Activating Token Index: 655

Text #10

Max Range: 0.4507. Min Range: -0.4507

Max Act: 0.3803. Min Act: -0.0000

Data Index: 934694 (The Pile)

Max Activating Token Index: 858

Text #11

Max Range: 0.4507. Min Range: -0.4507

Max Act: 0.3786. Min Act: -0.0000

Data Index: 1002584 (The Pile)

Max Activating Token Index: 655

Text #12

Max Range: 0.4507. Min Range: -0.4507

Max Act: 0.3571. Min Act: -0.0000

Data Index: 1658679 (The Pile)

Max Activating Token Index: 897

Text #13

Max Range: 0.4507. Min Range: -0.4507

Max Act: 0.3657. Min Act: -0.0000

Data Index: 1203918 (The Pile)

Max Activating Token Index: 313

Text #14

Max Range: 0.4507. Min Range: -0.4507

Max Act: 0.3615. Min Act: -0.0000

Data Index: 776911 (The Pile)

Max Activating Token Index: 86

Text #15

Max Range: 0.4507. Min Range: -0.4507

Max Act: 0.3592. Min Act: -0.0000

Data Index: 1681292 (The Pile)

Max Activating Token Index: 945

Text #16

Max Range: 0.4507. Min Range: -0.4507

Max Act: 0.3648. Min Act: -0.0000

Data Index: 1066500 (The Pile)

Max Activating Token Index: 67

Text #17

Max Range: 0.4507. Min Range: -0.4507

Max Act: 0.3662. Min Act: -0.0000

Data Index: 602757 (The Pile)

Max Activating Token Index: 857

Text #18

Max Range: 0.4507. Min Range: -0.4507

Max Act: 0.3639. Min Act: -0.0000

Data Index: 1882876 (The Pile)

Max Activating Token Index: 62

Text #19

Max Range: 0.4507. Min Range: -0.4507

Max Act: 0.3267. Min Act: -0.0000

Data Index: 1991295 (The Pile)

Max Activating Token Index: 739