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

Dataset: The Pile

Neuron 3596 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5825. Min Range: -0.5825

Max Act: 0.5687. Min Act: -0.0000

Data Index: 1057654 (The Pile)

Max Activating Token Index: 662

Text #1

Max Range: 0.5825. Min Range: -0.5825

Max Act: 0.5825. Min Act: -0.0000

Data Index: 1236167 (The Pile)

Max Activating Token Index: 136

Text #2

Max Range: 0.5825. Min Range: -0.5825

Max Act: 0.4858. Min Act: -0.0000

Data Index: 1966097 (The Pile)

Max Activating Token Index: 463

Text #3

Max Range: 0.5825. Min Range: -0.5825

Max Act: 0.4018. Min Act: -0.0000

Data Index: 357669 (The Pile)

Max Activating Token Index: 668

Text #4

Max Range: 0.5825. Min Range: -0.5825

Max Act: 0.3986. Min Act: -0.0000

Data Index: 1525764 (The Pile)

Max Activating Token Index: 739

Text #5

Max Range: 0.5825. Min Range: -0.5825

Max Act: 0.3517. Min Act: -0.0000

Data Index: 1667544 (The Pile)

Max Activating Token Index: 540

Text #6

Max Range: 0.5825. Min Range: -0.5825

Max Act: 0.4027. Min Act: -0.0000

Data Index: 1649094 (The Pile)

Max Activating Token Index: 87

Text #7

Max Range: 0.5825. Min Range: -0.5825

Max Act: 0.4194. Min Act: -0.0000

Data Index: 1752424 (The Pile)

Max Activating Token Index: 928

Text #8

Max Range: 0.5825. Min Range: -0.5825

Max Act: 0.3735. Min Act: -0.0000

Data Index: 156718 (The Pile)

Max Activating Token Index: 949

Text #9

Max Range: 0.5825. Min Range: -0.5825

Max Act: 0.3822. Min Act: -0.0000

Data Index: 1206187 (The Pile)

Max Activating Token Index: 255

Text #10

Max Range: 0.5825. Min Range: -0.5825

Max Act: 0.3361. Min Act: -0.0000

Data Index: 22572 (The Pile)

Max Activating Token Index: 232

Text #11

Max Range: 0.5825. Min Range: -0.5825

Max Act: 0.3683. Min Act: -0.0000

Data Index: 617545 (The Pile)

Max Activating Token Index: 1016

Text #12

Max Range: 0.5825. Min Range: -0.5825

Max Act: 0.3573. Min Act: -0.0000

Data Index: 1671517 (The Pile)

Max Activating Token Index: 919

Text #13

Max Range: 0.5825. Min Range: -0.5825

Max Act: 0.3634. Min Act: -0.0000

Data Index: 1109703 (The Pile)

Max Activating Token Index: 933

Text #14

Max Range: 0.5825. Min Range: -0.5825

Max Act: 0.3144. Min Act: -0.0000

Data Index: 1616850 (The Pile)

Max Activating Token Index: 602

Text #15

Max Range: 0.5825. Min Range: -0.5825

Max Act: 0.3574. Min Act: -0.0000

Data Index: 837261 (The Pile)

Max Activating Token Index: 622

Text #16

Max Range: 0.5825. Min Range: -0.5825

Max Act: 0.3490. Min Act: -0.0000

Data Index: 1789164 (The Pile)

Max Activating Token Index: 949

Text #17

Max Range: 0.5825. Min Range: -0.5825

Max Act: 0.3625. Min Act: -0.0000

Data Index: 1915848 (The Pile)

Max Activating Token Index: 756

Text #18

Max Range: 0.5825. Min Range: -0.5825

Max Act: 0.3362. Min Act: -0.0000

Data Index: 1948518 (The Pile)

Max Activating Token Index: 211

Text #19

Max Range: 0.5825. Min Range: -0.5825

Max Act: 0.3748. Min Act: -0.0000

Data Index: 325745 (The Pile)

Max Activating Token Index: 503