Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2480 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.9098. Min Range: -3.9098

Max Act: 3.9098. Min Act: -0.0000

Data Index: 487123 (C4 (Web Text))

Max Activating Token Index: 992

Text #1

Max Range: 3.9098. Min Range: -3.9098

Max Act: 3.3936. Min Act: -0.0000

Data Index: 332587 (C4 (Web Text))

Max Activating Token Index: 940

Text #2

Max Range: 3.9098. Min Range: -3.9098

Max Act: 3.0812. Min Act: -0.0000

Data Index: 800863 (C4 (Web Text))

Max Activating Token Index: 863

Text #3

Max Range: 3.9098. Min Range: -3.9098

Max Act: 3.4528. Min Act: -0.0000

Data Index: 374316 (C4 (Web Text))

Max Activating Token Index: 749

Text #4

Max Range: 3.9098. Min Range: -3.9098

Max Act: 3.0573. Min Act: -0.0000

Data Index: 675824 (C4 (Web Text))

Max Activating Token Index: 691

Text #5

Max Range: 3.9098. Min Range: -3.9098

Max Act: 3.2749. Min Act: -0.0000

Data Index: 618998 (C4 (Web Text))

Max Activating Token Index: 129

Text #6

Max Range: 3.9098. Min Range: -3.9098

Max Act: 3.0414. Min Act: -0.0000

Data Index: 277425 (C4 (Web Text))

Max Activating Token Index: 808

Text #7

Max Range: 3.9098. Min Range: -3.9098

Max Act: 3.0105. Min Act: -0.0000

Data Index: 656558 (C4 (Web Text))

Max Activating Token Index: 639

Text #8

Max Range: 3.9098. Min Range: -3.9098

Max Act: 3.0667. Min Act: -0.0000

Data Index: 1084480 (C4 (Web Text))

Max Activating Token Index: 1004

Text #9

Max Range: 3.9098. Min Range: -3.9098

Max Act: 2.9296. Min Act: -0.0000

Data Index: 149819 (C4 (Web Text))

Max Activating Token Index: 460

Text #10

Max Range: 3.9098. Min Range: -3.9098

Max Act: 2.8499. Min Act: -0.0000

Data Index: 1246350 (C4 (Web Text))

Max Activating Token Index: 865

Text #11

Max Range: 3.9098. Min Range: -3.9098

Max Act: 2.6808. Min Act: -0.0000

Data Index: 1253505 (C4 (Web Text))

Max Activating Token Index: 281

Text #12

Max Range: 3.9098. Min Range: -3.9098

Max Act: 3.0058. Min Act: -0.0000

Data Index: 273370 (C4 (Web Text))

Max Activating Token Index: 705

Text #13

Max Range: 3.9098. Min Range: -3.9098

Max Act: 2.7055. Min Act: -0.0000

Data Index: 1163702 (C4 (Web Text))

Max Activating Token Index: 802

Text #14

Max Range: 3.9098. Min Range: -3.9098

Max Act: 2.9516. Min Act: -0.0000

Data Index: 1273123 (C4 (Web Text))

Max Activating Token Index: 327

Text #15

Max Range: 3.9098. Min Range: -3.9098

Max Act: 2.6325. Min Act: -0.0000

Data Index: 561166 (C4 (Web Text))

Max Activating Token Index: 537

Text #16

Max Range: 3.9098. Min Range: -3.9098

Max Act: 2.5778. Min Act: -0.0000

Data Index: 337290 (C4 (Web Text))

Max Activating Token Index: 554

Text #17

Max Range: 3.9098. Min Range: -3.9098

Max Act: 2.6486. Min Act: -0.0000

Data Index: 917852 (C4 (Web Text))

Max Activating Token Index: 875

Text #18

Max Range: 3.9098. Min Range: -3.9098

Max Act: 2.6444. Min Act: -0.0000

Data Index: 2660 (C4 (Web Text))

Max Activating Token Index: 992

Text #19

Max Range: 3.9098. Min Range: -3.9098

Max Act: 2.5632. Min Act: -0.0000

Data Index: 917190 (C4 (Web Text))

Max Activating Token Index: 524