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

Dataset: The Pile

Neuron 3635 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: 0.3138. Min Range: -0.3138

Max Act: 0.3138. Min Act: -0.0000

Data Index: 1402265 (The Pile)

Max Activating Token Index: 913

Text #1

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.2618. Min Act: -0.0000

Data Index: 251944 (The Pile)

Max Activating Token Index: 791

Text #2

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.2627. Min Act: -0.0000

Data Index: 1832733 (The Pile)

Max Activating Token Index: 286

Text #3

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.2798. Min Act: -0.0000

Data Index: 1552795 (The Pile)

Max Activating Token Index: 703

Text #4

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.2464. Min Act: -0.0000

Data Index: 879266 (The Pile)

Max Activating Token Index: 469

Text #5

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.2359. Min Act: -0.0000

Data Index: 853992 (The Pile)

Max Activating Token Index: 504

Text #6

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.2451. Min Act: -0.0000

Data Index: 511524 (The Pile)

Max Activating Token Index: 302

Text #7

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.2286. Min Act: -0.0000

Data Index: 513461 (The Pile)

Max Activating Token Index: 736

Text #8

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.2385. Min Act: -0.0000

Data Index: 1432777 (The Pile)

Max Activating Token Index: 79

Text #9

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.2299. Min Act: -0.0000

Data Index: 878148 (The Pile)

Max Activating Token Index: 357

Text #10

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.2301. Min Act: -0.0000

Data Index: 253739 (The Pile)

Max Activating Token Index: 619

Text #11

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.2364. Min Act: -0.0000

Data Index: 1596635 (The Pile)

Max Activating Token Index: 401

Text #12

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.2315. Min Act: -0.0000

Data Index: 488867 (The Pile)

Max Activating Token Index: 375

Text #13

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.2370. Min Act: -0.0000

Data Index: 1664191 (The Pile)

Max Activating Token Index: 913

Text #14

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.2319. Min Act: -0.0000

Data Index: 1252631 (The Pile)

Max Activating Token Index: 687

Text #15

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.2289. Min Act: -0.0000

Data Index: 147192 (The Pile)

Max Activating Token Index: 827

Text #16

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.2200. Min Act: -0.0000

Data Index: 1784229 (The Pile)

Max Activating Token Index: 967

Text #17

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.2280. Min Act: -0.0000

Data Index: 1229450 (The Pile)

Max Activating Token Index: 104

Text #18

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.2160. Min Act: -0.0000

Data Index: 1526573 (The Pile)

Max Activating Token Index: 730

Text #19

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.2310. Min Act: -0.0000

Data Index: 623468 (The Pile)

Max Activating Token Index: 312