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

Dataset: The Pile

Neuron 4701 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: 0.6392. Min Range: -0.6392

Max Act: 0.6392. Min Act: -0.0000

Data Index: 452736 (The Pile)

Max Activating Token Index: 436

Text #1

Max Range: 0.6392. Min Range: -0.6392

Max Act: 0.5243. Min Act: -0.0000

Data Index: 1445357 (The Pile)

Max Activating Token Index: 292

Text #2

Max Range: 0.6392. Min Range: -0.6392

Max Act: 0.5198. Min Act: -0.0000

Data Index: 1963248 (The Pile)

Max Activating Token Index: 891

Text #3

Max Range: 0.6392. Min Range: -0.6392

Max Act: 0.5186. Min Act: -0.0000

Data Index: 917822 (The Pile)

Max Activating Token Index: 211

Text #4

Max Range: 0.6392. Min Range: -0.6392

Max Act: 0.5073. Min Act: -0.0000

Data Index: 1305876 (The Pile)

Max Activating Token Index: 118

Text #5

Max Range: 0.6392. Min Range: -0.6392

Max Act: 0.4515. Min Act: -0.0000

Data Index: 1006382 (The Pile)

Max Activating Token Index: 725

Text #6

Max Range: 0.6392. Min Range: -0.6392

Max Act: 0.4500. Min Act: -0.0000

Data Index: 324543 (The Pile)

Max Activating Token Index: 151

Text #7

Max Range: 0.6392. Min Range: -0.6392

Max Act: 0.4524. Min Act: -0.0000

Data Index: 1787942 (The Pile)

Max Activating Token Index: 918

Text #8

Max Range: 0.6392. Min Range: -0.6392

Max Act: 0.4243. Min Act: -0.0000

Data Index: 1095490 (The Pile)

Max Activating Token Index: 246

Text #9

Max Range: 0.6392. Min Range: -0.6392

Max Act: 0.4331. Min Act: -0.0000

Data Index: 972595 (The Pile)

Max Activating Token Index: 347

Text #10

Max Range: 0.6392. Min Range: -0.6392

Max Act: 0.4402. Min Act: -0.0000

Data Index: 1236149 (The Pile)

Max Activating Token Index: 658

Text #11

Max Range: 0.6392. Min Range: -0.6392

Max Act: 0.4310. Min Act: -0.0000

Data Index: 1100485 (The Pile)

Max Activating Token Index: 491

Text #12

Max Range: 0.6392. Min Range: -0.6392

Max Act: 0.4084. Min Act: -0.0000

Data Index: 1736719 (The Pile)

Max Activating Token Index: 469

Text #13

Max Range: 0.6392. Min Range: -0.6392

Max Act: 0.4340. Min Act: -0.0000

Data Index: 78873 (The Pile)

Max Activating Token Index: 956

Text #14

Max Range: 0.6392. Min Range: -0.6392

Max Act: 0.4074. Min Act: -0.0000

Data Index: 395854 (The Pile)

Max Activating Token Index: 762

Text #15

Max Range: 0.6392. Min Range: -0.6392

Max Act: 0.4187. Min Act: -0.0000

Data Index: 1693281 (The Pile)

Max Activating Token Index: 816

Text #16

Max Range: 0.6392. Min Range: -0.6392

Max Act: 0.3952. Min Act: -0.0000

Data Index: 1276924 (The Pile)

Max Activating Token Index: 950

Text #17

Max Range: 0.6392. Min Range: -0.6392

Max Act: 0.4015. Min Act: -0.0000

Data Index: 1743507 (The Pile)

Max Activating Token Index: 559

Text #18

Max Range: 0.6392. Min Range: -0.6392

Max Act: 0.3754. Min Act: 0.0000

Data Index: 628574 (The Pile)

Max Activating Token Index: 961

Text #19

Max Range: 0.6392. Min Range: -0.6392

Max Act: 0.4097. Min Act: -0.0000

Data Index: 991835 (The Pile)

Max Activating Token Index: 592