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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3508 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5038. Min Range: -2.5038

Max Act: 2.5038. Min Act: -0.0000

Data Index: 255715 (C4 (Web Text))

Max Activating Token Index: 1014

Text #1

Max Range: 2.5038. Min Range: -2.5038

Max Act: 1.9536. Min Act: -0.0000

Data Index: 607318 (C4 (Web Text))

Max Activating Token Index: 747

Text #2

Max Range: 2.5038. Min Range: -2.5038

Max Act: 1.9189. Min Act: 0.0000

Data Index: 464509 (C4 (Web Text))

Max Activating Token Index: 269

Text #3

Max Range: 2.5038. Min Range: -2.5038

Max Act: 1.9687. Min Act: -0.0000

Data Index: 33881 (C4 (Web Text))

Max Activating Token Index: 450

Text #4

Max Range: 2.5038. Min Range: -2.5038

Max Act: 1.8407. Min Act: -0.0000

Data Index: 889623 (C4 (Web Text))

Max Activating Token Index: 650

Text #5

Max Range: 2.5038. Min Range: -2.5038

Max Act: 1.6956. Min Act: -0.0000

Data Index: 243924 (C4 (Web Text))

Max Activating Token Index: 84

Text #6

Max Range: 2.5038. Min Range: -2.5038

Max Act: 1.8740. Min Act: -0.0000

Data Index: 489650 (C4 (Web Text))

Max Activating Token Index: 482

Text #7

Max Range: 2.5038. Min Range: -2.5038

Max Act: 1.7440. Min Act: -0.0000

Data Index: 475185 (C4 (Web Text))

Max Activating Token Index: 463

Text #8

Max Range: 2.5038. Min Range: -2.5038

Max Act: 1.9232. Min Act: -0.0000

Data Index: 1063170 (C4 (Web Text))

Max Activating Token Index: 261

Text #9

Max Range: 2.5038. Min Range: -2.5038

Max Act: 1.6420. Min Act: -0.0000

Data Index: 227118 (C4 (Web Text))

Max Activating Token Index: 359

Text #10

Max Range: 2.5038. Min Range: -2.5038

Max Act: 1.6111. Min Act: -0.0000

Data Index: 466628 (C4 (Web Text))

Max Activating Token Index: 267

Text #11

Max Range: 2.5038. Min Range: -2.5038

Max Act: 1.6124. Min Act: -0.0000

Data Index: 437439 (C4 (Web Text))

Max Activating Token Index: 786

Text #12

Max Range: 2.5038. Min Range: -2.5038

Max Act: 1.5097. Min Act: -0.0000

Data Index: 661163 (C4 (Web Text))

Max Activating Token Index: 640

Text #13

Max Range: 2.5038. Min Range: -2.5038

Max Act: 1.4433. Min Act: -0.0000

Data Index: 794090 (C4 (Web Text))

Max Activating Token Index: 490

Text #14

Max Range: 2.5038. Min Range: -2.5038

Max Act: 1.5744. Min Act: -0.0000

Data Index: 211350 (C4 (Web Text))

Max Activating Token Index: 607

Text #15

Max Range: 2.5038. Min Range: -2.5038

Max Act: 1.5543. Min Act: -0.0000

Data Index: 651441 (C4 (Web Text))

Max Activating Token Index: 971

Text #16

Max Range: 2.5038. Min Range: -2.5038

Max Act: 1.4513. Min Act: -0.0000

Data Index: 968541 (C4 (Web Text))

Max Activating Token Index: 565

Text #17

Max Range: 2.5038. Min Range: -2.5038

Max Act: 1.5966. Min Act: -0.0000

Data Index: 730606 (C4 (Web Text))

Max Activating Token Index: 637

Text #18

Max Range: 2.5038. Min Range: -2.5038

Max Act: 1.3619. Min Act: -0.0000

Data Index: 586229 (C4 (Web Text))

Max Activating Token Index: 354

Text #19

Max Range: 2.5038. Min Range: -2.5038

Max Act: 1.2329. Min Act: -0.0000

Data Index: 698942 (C4 (Web Text))

Max Activating Token Index: 903