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

Dataset: The Pile

Neuron 4233 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4962. Min Range: -0.4962

Max Act: 0.4492. Min Act: -0.0000

Data Index: 751448 (The Pile)

Max Activating Token Index: 745

Text #1

Max Range: 0.4962. Min Range: -0.4962

Max Act: 0.4962. Min Act: -0.0000

Data Index: 1469319 (The Pile)

Max Activating Token Index: 778

Text #2

Max Range: 0.4962. Min Range: -0.4962

Max Act: 0.4703. Min Act: -0.0000

Data Index: 756161 (The Pile)

Max Activating Token Index: 403

Text #3

Max Range: 0.4962. Min Range: -0.4962

Max Act: 0.4767. Min Act: -0.0000

Data Index: 176359 (The Pile)

Max Activating Token Index: 958

Text #4

Max Range: 0.4962. Min Range: -0.4962

Max Act: 0.4475. Min Act: -0.0000

Data Index: 933944 (The Pile)

Max Activating Token Index: 810

Text #5

Max Range: 0.4962. Min Range: -0.4962

Max Act: 0.4166. Min Act: -0.0000

Data Index: 1209172 (The Pile)

Max Activating Token Index: 502

Text #6

Max Range: 0.4962. Min Range: -0.4962

Max Act: 0.3916. Min Act: -0.0000

Data Index: 1552097 (The Pile)

Max Activating Token Index: 599

Text #7

Max Range: 0.4962. Min Range: -0.4962

Max Act: 0.3837. Min Act: -0.0000

Data Index: 1789324 (The Pile)

Max Activating Token Index: 856

Text #8

Max Range: 0.4962. Min Range: -0.4962

Max Act: 0.3737. Min Act: -0.0000

Data Index: 459257 (The Pile)

Max Activating Token Index: 252

Text #9

Max Range: 0.4962. Min Range: -0.4962

Max Act: 0.3812. Min Act: -0.0000

Data Index: 974519 (The Pile)

Max Activating Token Index: 1022

Text #10

Max Range: 0.4962. Min Range: -0.4962

Max Act: 0.3734. Min Act: -0.0000

Data Index: 354724 (The Pile)

Max Activating Token Index: 637

Text #11

Max Range: 0.4962. Min Range: -0.4962

Max Act: 0.4065. Min Act: -0.0000

Data Index: 873980 (The Pile)

Max Activating Token Index: 897

Text #12

Max Range: 0.4962. Min Range: -0.4962

Max Act: 0.3685. Min Act: -0.0000

Data Index: 660748 (The Pile)

Max Activating Token Index: 949

Text #13

Max Range: 0.4962. Min Range: -0.4962

Max Act: 0.3753. Min Act: -0.0000

Data Index: 43751 (The Pile)

Max Activating Token Index: 686

Text #14

Max Range: 0.4962. Min Range: -0.4962

Max Act: 0.3905. Min Act: -0.0000

Data Index: 264509 (The Pile)

Max Activating Token Index: 993

Text #15

Max Range: 0.4962. Min Range: -0.4962

Max Act: 0.3487. Min Act: -0.0000

Data Index: 1337062 (The Pile)

Max Activating Token Index: 407

Text #16

Max Range: 0.4962. Min Range: -0.4962

Max Act: 0.3305. Min Act: -0.0000

Data Index: 999482 (The Pile)

Max Activating Token Index: 780

Text #17

Max Range: 0.4962. Min Range: -0.4962

Max Act: 0.3531. Min Act: -0.0000

Data Index: 336155 (The Pile)

Max Activating Token Index: 411

Text #18

Max Range: 0.4962. Min Range: -0.4962

Max Act: 0.3424. Min Act: -0.0000

Data Index: 1204529 (The Pile)

Max Activating Token Index: 306

Text #19

Max Range: 0.4962. Min Range: -0.4962

Max Act: 0.3592. Min Act: -0.0000

Data Index: 380104 (The Pile)

Max Activating Token Index: 439