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

Dataset: The Pile

Neuron 2177 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: 0.6059. Min Range: -0.6059

Max Act: 0.5707. Min Act: -0.0000

Data Index: 1666254 (The Pile)

Max Activating Token Index: 144

Text #1

Max Range: 0.6059. Min Range: -0.6059

Max Act: 0.5001. Min Act: -0.0000

Data Index: 10410 (The Pile)

Max Activating Token Index: 744

Text #2

Max Range: 0.6059. Min Range: -0.6059

Max Act: 0.5132. Min Act: -0.0000

Data Index: 1045189 (The Pile)

Max Activating Token Index: 439

Text #3

Max Range: 0.6059. Min Range: -0.6059

Max Act: 0.6059. Min Act: -0.0000

Data Index: 1224636 (The Pile)

Max Activating Token Index: 544

Text #4

Max Range: 0.6059. Min Range: -0.6059

Max Act: 0.5099. Min Act: -0.0000

Data Index: 1390430 (The Pile)

Max Activating Token Index: 457

Text #5

Max Range: 0.6059. Min Range: -0.6059

Max Act: 0.5492. Min Act: -0.0000

Data Index: 394132 (The Pile)

Max Activating Token Index: 388

Text #6

Max Range: 0.6059. Min Range: -0.6059

Max Act: 0.5230. Min Act: -0.0000

Data Index: 1770017 (The Pile)

Max Activating Token Index: 433

Text #7

Max Range: 0.6059. Min Range: -0.6059

Max Act: 0.5139. Min Act: -0.0000

Data Index: 1346024 (The Pile)

Max Activating Token Index: 701

Text #8

Max Range: 0.6059. Min Range: -0.6059

Max Act: 0.5295. Min Act: -0.0000

Data Index: 760289 (The Pile)

Max Activating Token Index: 489

Text #9

Max Range: 0.6059. Min Range: -0.6059

Max Act: 0.4531. Min Act: -0.0000

Data Index: 283503 (The Pile)

Max Activating Token Index: 285

Text #10

Max Range: 0.6059. Min Range: -0.6059

Max Act: 0.4970. Min Act: -0.0000

Data Index: 240136 (The Pile)

Max Activating Token Index: 271

Text #11

Max Range: 0.6059. Min Range: -0.6059

Max Act: 0.4604. Min Act: -0.0000

Data Index: 830861 (The Pile)

Max Activating Token Index: 252

Text #12

Max Range: 0.6059. Min Range: -0.6059

Max Act: 0.4961. Min Act: -0.0000

Data Index: 1522613 (The Pile)

Max Activating Token Index: 449

Text #13

Max Range: 0.6059. Min Range: -0.6059

Max Act: 0.4241. Min Act: -0.0000

Data Index: 213917 (The Pile)

Max Activating Token Index: 320

Text #14

Max Range: 0.6059. Min Range: -0.6059

Max Act: 0.4525. Min Act: -0.0000

Data Index: 884379 (The Pile)

Max Activating Token Index: 836

Text #15

Max Range: 0.6059. Min Range: -0.6059

Max Act: 0.4406. Min Act: -0.0000

Data Index: 525506 (The Pile)

Max Activating Token Index: 616

Text #16

Max Range: 0.6059. Min Range: -0.6059

Max Act: 0.4648. Min Act: -0.0000

Data Index: 1620470 (The Pile)

Max Activating Token Index: 560

Text #17

Max Range: 0.6059. Min Range: -0.6059

Max Act: 0.4390. Min Act: -0.0000

Data Index: 818212 (The Pile)

Max Activating Token Index: 665

Text #18

Max Range: 0.6059. Min Range: -0.6059

Max Act: 0.4269. Min Act: -0.0000

Data Index: 1112124 (The Pile)

Max Activating Token Index: 500

Text #19

Max Range: 0.6059. Min Range: -0.6059

Max Act: 0.4311. Min Act: -0.0000

Data Index: 1005154 (The Pile)

Max Activating Token Index: 105