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

Dataset: The Pile

Neuron 4771 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0372. Min Act: -0.0000

Data Index: 83719 (The Pile)

Max Activating Token Index: 732

Text #1

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0350. Min Act: -0.0000

Data Index: 79365 (The Pile)

Max Activating Token Index: 704

Text #2

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0346. Min Act: -0.0000

Data Index: 79339 (The Pile)

Max Activating Token Index: 908

Text #3

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0333. Min Act: -0.0000

Data Index: 758529 (The Pile)

Max Activating Token Index: 787

Text #4

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0349. Min Act: -0.0000

Data Index: 1150826 (The Pile)

Max Activating Token Index: 607

Text #5

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0340. Min Act: -0.0000

Data Index: 219794 (The Pile)

Max Activating Token Index: 755

Text #6

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0338. Min Act: -0.0000

Data Index: 1899218 (The Pile)

Max Activating Token Index: 699

Text #7

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0349. Min Act: -0.0000

Data Index: 1668910 (The Pile)

Max Activating Token Index: 607

Text #8

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0335. Min Act: -0.0000

Data Index: 913548 (The Pile)

Max Activating Token Index: 807

Text #9

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0321. Min Act: -0.0000

Data Index: 125232 (The Pile)

Max Activating Token Index: 721

Text #10

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0331. Min Act: -0.0000

Data Index: 411166 (The Pile)

Max Activating Token Index: 928

Text #11

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0341. Min Act: -0.0000

Data Index: 974502 (The Pile)

Max Activating Token Index: 640

Text #12

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0327. Min Act: -0.0000

Data Index: 679133 (The Pile)

Max Activating Token Index: 655

Text #13

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0322. Min Act: -0.0000

Data Index: 1226811 (The Pile)

Max Activating Token Index: 752

Text #14

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0327. Min Act: -0.0000

Data Index: 771839 (The Pile)

Max Activating Token Index: 687

Text #15

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0326. Min Act: -0.0000

Data Index: 1722877 (The Pile)

Max Activating Token Index: 665

Text #16

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0335. Min Act: -0.0000

Data Index: 1988204 (The Pile)

Max Activating Token Index: 630

Text #17

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0317. Min Act: -0.0000

Data Index: 1827453 (The Pile)

Max Activating Token Index: 805

Text #18

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0338. Min Act: -0.0000

Data Index: 482414 (The Pile)

Max Activating Token Index: 698

Text #19

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0330. Min Act: -0.0000

Data Index: 645911 (The Pile)

Max Activating Token Index: 671