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

Dataset: The Pile

Neuron 3214 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: 0.3503. Min Range: -0.3503

Max Act: 0.3503. Min Act: -0.0000

Data Index: 1250301 (The Pile)

Max Activating Token Index: 193

Text #1

Max Range: 0.3503. Min Range: -0.3503

Max Act: 0.2975. Min Act: -0.0000

Data Index: 406999 (The Pile)

Max Activating Token Index: 889

Text #2

Max Range: 0.3503. Min Range: -0.3503

Max Act: 0.2963. Min Act: -0.0000

Data Index: 1482697 (The Pile)

Max Activating Token Index: 260

Text #3

Max Range: 0.3503. Min Range: -0.3503

Max Act: 0.2744. Min Act: -0.0000

Data Index: 1208445 (The Pile)

Max Activating Token Index: 398

Text #4

Max Range: 0.3503. Min Range: -0.3503

Max Act: 0.2776. Min Act: -0.0000

Data Index: 63205 (The Pile)

Max Activating Token Index: 663

Text #5

Max Range: 0.3503. Min Range: -0.3503

Max Act: 0.3023. Min Act: -0.0000

Data Index: 1545101 (The Pile)

Max Activating Token Index: 951

Text #6

Max Range: 0.3503. Min Range: -0.3503

Max Act: 0.2851. Min Act: -0.0000

Data Index: 330291 (The Pile)

Max Activating Token Index: 94

Text #7

Max Range: 0.3503. Min Range: -0.3503

Max Act: 0.2458. Min Act: -0.0000

Data Index: 819691 (The Pile)

Max Activating Token Index: 659

Text #8

Max Range: 0.3503. Min Range: -0.3503

Max Act: 0.2352. Min Act: -0.0000

Data Index: 1179312 (The Pile)

Max Activating Token Index: 743

Text #9

Max Range: 0.3503. Min Range: -0.3503

Max Act: 0.2470. Min Act: -0.0000

Data Index: 944777 (The Pile)

Max Activating Token Index: 658

Text #10

Max Range: 0.3503. Min Range: -0.3503

Max Act: 0.2159. Min Act: -0.0000

Data Index: 344479 (The Pile)

Max Activating Token Index: 884

Text #11

Max Range: 0.3503. Min Range: -0.3503

Max Act: 0.2209. Min Act: -0.0000

Data Index: 1560337 (The Pile)

Max Activating Token Index: 751

Text #12

Max Range: 0.3503. Min Range: -0.3503

Max Act: 0.2279. Min Act: -0.0000

Data Index: 1815701 (The Pile)

Max Activating Token Index: 295

Text #13

Max Range: 0.3503. Min Range: -0.3503

Max Act: 0.2172. Min Act: -0.0000

Data Index: 373185 (The Pile)

Max Activating Token Index: 249

Text #14

Max Range: 0.3503. Min Range: -0.3503

Max Act: 0.2313. Min Act: -0.0000

Data Index: 1004416 (The Pile)

Max Activating Token Index: 359

Text #15

Max Range: 0.3503. Min Range: -0.3503

Max Act: 0.2110. Min Act: -0.0000

Data Index: 1230173 (The Pile)

Max Activating Token Index: 890

Text #16

Max Range: 0.3503. Min Range: -0.3503

Max Act: 0.2210. Min Act: -0.0000

Data Index: 337054 (The Pile)

Max Activating Token Index: 564

Text #17

Max Range: 0.3503. Min Range: -0.3503

Max Act: 0.2278. Min Act: -0.0000

Data Index: 732724 (The Pile)

Max Activating Token Index: 699

Text #18

Max Range: 0.3503. Min Range: -0.3503

Max Act: 0.2053. Min Act: -0.0000

Data Index: 1800314 (The Pile)

Max Activating Token Index: 737

Text #19

Max Range: 0.3503. Min Range: -0.3503

Max Act: 0.2397. Min Act: -0.0000

Data Index: 516885 (The Pile)

Max Activating Token Index: 163