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

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

Neuron 5717 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: 0.9075. Min Range: -0.9075

Max Act: 0.9075. Min Act: -0.0000

Data Index: 1274079 (C4 (Web Text))

Max Activating Token Index: 450

Text #1

Max Range: 0.9075. Min Range: -0.9075

Max Act: 0.8812. Min Act: -0.0000

Data Index: 100480 (C4 (Web Text))

Max Activating Token Index: 265

Text #2

Max Range: 0.9075. Min Range: -0.9075

Max Act: 0.8645. Min Act: -0.0000

Data Index: 887491 (C4 (Web Text))

Max Activating Token Index: 252

Text #3

Max Range: 0.9075. Min Range: -0.9075

Max Act: 0.7409. Min Act: -0.0000

Data Index: 1111820 (C4 (Web Text))

Max Activating Token Index: 643

Text #4

Max Range: 0.9075. Min Range: -0.9075

Max Act: 0.7600. Min Act: -0.0000

Data Index: 30016 (C4 (Web Text))

Max Activating Token Index: 512

Text #5

Max Range: 0.9075. Min Range: -0.9075

Max Act: 0.7513. Min Act: -0.0000

Data Index: 463305 (C4 (Web Text))

Max Activating Token Index: 538

Text #6

Max Range: 0.9075. Min Range: -0.9075

Max Act: 0.7441. Min Act: -0.0000

Data Index: 1275756 (C4 (Web Text))

Max Activating Token Index: 98

Text #7

Max Range: 0.9075. Min Range: -0.9075

Max Act: 0.7027. Min Act: -0.0000

Data Index: 851807 (C4 (Web Text))

Max Activating Token Index: 100

Text #8

Max Range: 0.9075. Min Range: -0.9075

Max Act: 0.7444. Min Act: -0.0000

Data Index: 736464 (C4 (Web Text))

Max Activating Token Index: 325

Text #9

Max Range: 0.9075. Min Range: -0.9075

Max Act: 0.6950. Min Act: -0.0000

Data Index: 399132 (C4 (Web Text))

Max Activating Token Index: 771

Text #10

Max Range: 0.9075. Min Range: -0.9075

Max Act: 0.7434. Min Act: -0.0000

Data Index: 1277574 (C4 (Web Text))

Max Activating Token Index: 816

Text #11

Max Range: 0.9075. Min Range: -0.9075

Max Act: 0.6829. Min Act: -0.0000

Data Index: 1268944 (C4 (Web Text))

Max Activating Token Index: 592

Text #12

Max Range: 0.9075. Min Range: -0.9075

Max Act: 0.7205. Min Act: -0.0000

Data Index: 1281045 (C4 (Web Text))

Max Activating Token Index: 798

Text #13

Max Range: 0.9075. Min Range: -0.9075

Max Act: 0.6950. Min Act: -0.0000

Data Index: 188525 (C4 (Web Text))

Max Activating Token Index: 842

Text #14

Max Range: 0.9075. Min Range: -0.9075

Max Act: 0.6514. Min Act: -0.0000

Data Index: 1126111 (C4 (Web Text))

Max Activating Token Index: 818

Text #15

Max Range: 0.9075. Min Range: -0.9075

Max Act: 0.6852. Min Act: -0.0000

Data Index: 8626 (C4 (Web Text))

Max Activating Token Index: 564

Text #16

Max Range: 0.9075. Min Range: -0.9075

Max Act: 0.6664. Min Act: -0.0000

Data Index: 1112018 (C4 (Web Text))

Max Activating Token Index: 591

Text #17

Max Range: 0.9075. Min Range: -0.9075

Max Act: 0.6813. Min Act: -0.0000

Data Index: 1199759 (C4 (Web Text))

Max Activating Token Index: 460

Text #18

Max Range: 0.9075. Min Range: -0.9075

Max Act: 0.6320. Min Act: -0.0000

Data Index: 534346 (C4 (Web Text))

Max Activating Token Index: 72

Text #19

Max Range: 0.9075. Min Range: -0.9075

Max Act: 0.7131. Min Act: -0.0000

Data Index: 977584 (C4 (Web Text))

Max Activating Token Index: 782