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

Dataset: The Pile

Neuron 99 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4221. Min Range: -1.4221

Max Act: 1.4221. Min Act: -0.0000

Data Index: 569787 (The Pile)

Max Activating Token Index: 320

Text #1

Max Range: 1.4221. Min Range: -1.4221

Max Act: 1.3866. Min Act: -0.0000

Data Index: 495782 (The Pile)

Max Activating Token Index: 769

Text #2

Max Range: 1.4221. Min Range: -1.4221

Max Act: 1.2207. Min Act: -0.0000

Data Index: 1594343 (The Pile)

Max Activating Token Index: 586

Text #3

Max Range: 1.4221. Min Range: -1.4221

Max Act: 1.2897. Min Act: -0.0000

Data Index: 497580 (The Pile)

Max Activating Token Index: 578

Text #4

Max Range: 1.4221. Min Range: -1.4221

Max Act: 1.3148. Min Act: -0.0000

Data Index: 1844462 (The Pile)

Max Activating Token Index: 116

Text #5

Max Range: 1.4221. Min Range: -1.4221

Max Act: 1.2357. Min Act: -0.0000

Data Index: 772354 (The Pile)

Max Activating Token Index: 828

Text #6

Max Range: 1.4221. Min Range: -1.4221

Max Act: 1.2926. Min Act: -0.0000

Data Index: 340416 (The Pile)

Max Activating Token Index: 188

Text #7

Max Range: 1.4221. Min Range: -1.4221

Max Act: 1.1363. Min Act: -0.0000

Data Index: 1077724 (The Pile)

Max Activating Token Index: 286

Text #8

Max Range: 1.4221. Min Range: -1.4221

Max Act: 1.1497. Min Act: -0.0000

Data Index: 568202 (The Pile)

Max Activating Token Index: 183

Text #9

Max Range: 1.4221. Min Range: -1.4221

Max Act: 1.2534. Min Act: -0.0000

Data Index: 671967 (The Pile)

Max Activating Token Index: 526

Text #10

Max Range: 1.4221. Min Range: -1.4221

Max Act: 1.2117. Min Act: -0.0000

Data Index: 1261828 (The Pile)

Max Activating Token Index: 370

Text #11

Max Range: 1.4221. Min Range: -1.4221

Max Act: 1.1345. Min Act: -0.0000

Data Index: 726456 (The Pile)

Max Activating Token Index: 622

Text #12

Max Range: 1.4221. Min Range: -1.4221

Max Act: 1.0476. Min Act: -0.0000

Data Index: 847723 (The Pile)

Max Activating Token Index: 554

Text #13

Max Range: 1.4221. Min Range: -1.4221

Max Act: 1.1629. Min Act: -0.0000

Data Index: 753087 (The Pile)

Max Activating Token Index: 332

Text #14

Max Range: 1.4221. Min Range: -1.4221

Max Act: 1.1224. Min Act: -0.0000

Data Index: 461500 (The Pile)

Max Activating Token Index: 761

Text #15

Max Range: 1.4221. Min Range: -1.4221

Max Act: 1.1265. Min Act: -0.0000

Data Index: 1726297 (The Pile)

Max Activating Token Index: 650

Text #16

Max Range: 1.4221. Min Range: -1.4221

Max Act: 1.1145. Min Act: -0.0000

Data Index: 1244560 (The Pile)

Max Activating Token Index: 602

Text #17

Max Range: 1.4221. Min Range: -1.4221

Max Act: 1.0734. Min Act: -0.0000

Data Index: 737504 (The Pile)

Max Activating Token Index: 238

Text #18

Max Range: 1.4221. Min Range: -1.4221

Max Act: 1.0699. Min Act: -0.0000

Data Index: 332545 (The Pile)

Max Activating Token Index: 735

Text #19

Max Range: 1.4221. Min Range: -1.4221

Max Act: 1.1107. Min Act: -0.0000

Data Index: 964859 (The Pile)

Max Activating Token Index: 799