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

Dataset: The Pile

Neuron 3636 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: 3.6704. Min Range: -3.6704

Max Act: 3.6704. Min Act: -0.0000

Data Index: 1357331 (The Pile)

Max Activating Token Index: 420

Text #1

Max Range: 3.6704. Min Range: -3.6704

Max Act: 3.2866. Min Act: -0.0000

Data Index: 715056 (The Pile)

Max Activating Token Index: 409

Text #2

Max Range: 3.6704. Min Range: -3.6704

Max Act: 3.2266. Min Act: -0.0000

Data Index: 1077213 (The Pile)

Max Activating Token Index: 170

Text #3

Max Range: 3.6704. Min Range: -3.6704

Max Act: 2.9668. Min Act: -0.0000

Data Index: 72714 (The Pile)

Max Activating Token Index: 346

Text #4

Max Range: 3.6704. Min Range: -3.6704

Max Act: 3.4590. Min Act: -0.0000

Data Index: 1061231 (The Pile)

Max Activating Token Index: 928

Text #5

Max Range: 3.6704. Min Range: -3.6704

Max Act: 2.9970. Min Act: -0.0000

Data Index: 145465 (The Pile)

Max Activating Token Index: 247

Text #6

Max Range: 3.6704. Min Range: -3.6704

Max Act: 3.0684. Min Act: -0.0000

Data Index: 1660538 (The Pile)

Max Activating Token Index: 103

Text #7

Max Range: 3.6704. Min Range: -3.6704

Max Act: 3.0608. Min Act: -0.0000

Data Index: 1661399 (The Pile)

Max Activating Token Index: 755

Text #8

Max Range: 3.6704. Min Range: -3.6704

Max Act: 3.3452. Min Act: -0.0000

Data Index: 930578 (The Pile)

Max Activating Token Index: 142

Text #9

Max Range: 3.6704. Min Range: -3.6704

Max Act: 2.6962. Min Act: -0.0000

Data Index: 1480608 (The Pile)

Max Activating Token Index: 697

Text #10

Max Range: 3.6704. Min Range: -3.6704

Max Act: 2.7472. Min Act: -0.0000

Data Index: 963876 (The Pile)

Max Activating Token Index: 198

Text #11

Max Range: 3.6704. Min Range: -3.6704

Max Act: 2.7084. Min Act: -0.0000

Data Index: 1771239 (The Pile)

Max Activating Token Index: 765

Text #12

Max Range: 3.6704. Min Range: -3.6704

Max Act: 2.6972. Min Act: -0.0000

Data Index: 1929750 (The Pile)

Max Activating Token Index: 659

Text #13

Max Range: 3.6704. Min Range: -3.6704

Max Act: 2.4511. Min Act: -0.0000

Data Index: 436460 (The Pile)

Max Activating Token Index: 925

Text #14

Max Range: 3.6704. Min Range: -3.6704

Max Act: 2.8031. Min Act: -0.0000

Data Index: 1217352 (The Pile)

Max Activating Token Index: 208

Text #15

Max Range: 3.6704. Min Range: -3.6704

Max Act: 2.7902. Min Act: -0.0000

Data Index: 1783190 (The Pile)

Max Activating Token Index: 572

Text #16

Max Range: 3.6704. Min Range: -3.6704

Max Act: 2.3516. Min Act: -0.0000

Data Index: 1043438 (The Pile)

Max Activating Token Index: 519

Text #17

Max Range: 3.6704. Min Range: -3.6704

Max Act: 2.8714. Min Act: -0.0000

Data Index: 1089456 (The Pile)

Max Activating Token Index: 301

Text #18

Max Range: 3.6704. Min Range: -3.6704

Max Act: 2.8321. Min Act: -0.0000

Data Index: 329717 (The Pile)

Max Activating Token Index: 684

Text #19

Max Range: 3.6704. Min Range: -3.6704

Max Act: 2.6942. Min Act: -0.0000

Data Index: 158734 (The Pile)

Max Activating Token Index: 541