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

Dataset: The Pile

Neuron 3225 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: 0.2964. Min Range: -0.2964

Max Act: 0.2964. Min Act: -0.0000

Data Index: 1897247 (The Pile)

Max Activating Token Index: 187

Text #1

Max Range: 0.2964. Min Range: -0.2964

Max Act: 0.2712. Min Act: -0.0000

Data Index: 532488 (The Pile)

Max Activating Token Index: 635

Text #2

Max Range: 0.2964. Min Range: -0.2964

Max Act: 0.2794. Min Act: -0.0000

Data Index: 883590 (The Pile)

Max Activating Token Index: 944

Text #3

Max Range: 0.2964. Min Range: -0.2964

Max Act: 0.2648. Min Act: -0.0000

Data Index: 667234 (The Pile)

Max Activating Token Index: 868

Text #4

Max Range: 0.2964. Min Range: -0.2964

Max Act: 0.2402. Min Act: -0.0000

Data Index: 47865 (The Pile)

Max Activating Token Index: 185

Text #5

Max Range: 0.2964. Min Range: -0.2964

Max Act: 0.2584. Min Act: -0.0000

Data Index: 1492775 (The Pile)

Max Activating Token Index: 654

Text #6

Max Range: 0.2964. Min Range: -0.2964

Max Act: 0.2377. Min Act: -0.0000

Data Index: 211952 (The Pile)

Max Activating Token Index: 898

Text #7

Max Range: 0.2964. Min Range: -0.2964

Max Act: 0.2358. Min Act: -0.0000

Data Index: 1649873 (The Pile)

Max Activating Token Index: 332

Text #8

Max Range: 0.2964. Min Range: -0.2964

Max Act: 0.2275. Min Act: -0.0000

Data Index: 569851 (The Pile)

Max Activating Token Index: 976

Text #9

Max Range: 0.2964. Min Range: -0.2964

Max Act: 0.2387. Min Act: -0.0000

Data Index: 679271 (The Pile)

Max Activating Token Index: 1009

Text #10

Max Range: 0.2964. Min Range: -0.2964

Max Act: 0.2218. Min Act: -0.0000

Data Index: 184863 (The Pile)

Max Activating Token Index: 480

Text #11

Max Range: 0.2964. Min Range: -0.2964

Max Act: 0.2377. Min Act: -0.0000

Data Index: 1948934 (The Pile)

Max Activating Token Index: 287

Text #12

Max Range: 0.2964. Min Range: -0.2964

Max Act: 0.2364. Min Act: -0.0000

Data Index: 1404798 (The Pile)

Max Activating Token Index: 717

Text #13

Max Range: 0.2964. Min Range: -0.2964

Max Act: 0.2367. Min Act: -0.0000

Data Index: 336557 (The Pile)

Max Activating Token Index: 503

Text #14

Max Range: 0.2964. Min Range: -0.2964

Max Act: 0.2366. Min Act: -0.0000

Data Index: 949175 (The Pile)

Max Activating Token Index: 785

Text #15

Max Range: 0.2964. Min Range: -0.2964

Max Act: 0.2359. Min Act: -0.0000

Data Index: 1667494 (The Pile)

Max Activating Token Index: 392

Text #16

Max Range: 0.2964. Min Range: -0.2964

Max Act: 0.2234. Min Act: -0.0000

Data Index: 1050863 (The Pile)

Max Activating Token Index: 22

Text #17

Max Range: 0.2964. Min Range: -0.2964

Max Act: 0.2359. Min Act: -0.0000

Data Index: 1902915 (The Pile)

Max Activating Token Index: 956

Text #18

Max Range: 0.2964. Min Range: -0.2964

Max Act: 0.2226. Min Act: -0.0000

Data Index: 1515601 (The Pile)

Max Activating Token Index: 616

Text #19

Max Range: 0.2964. Min Range: -0.2964

Max Act: 0.2264. Min Act: -0.0000

Data Index: 327947 (The Pile)

Max Activating Token Index: 223