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

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

Neuron 5894 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9684. Min Range: -0.9684

Max Act: 0.9684. Min Act: -0.0000

Data Index: 807261 (C4 (Web Text))

Max Activating Token Index: 318

Text #1

Max Range: 0.9684. Min Range: -0.9684

Max Act: 0.8226. Min Act: -0.0000

Data Index: 429298 (C4 (Web Text))

Max Activating Token Index: 43

Text #2

Max Range: 0.9684. Min Range: -0.9684

Max Act: 0.8645. Min Act: -0.0000

Data Index: 864265 (C4 (Web Text))

Max Activating Token Index: 818

Text #3

Max Range: 0.9684. Min Range: -0.9684

Max Act: 0.8844. Min Act: -0.0000

Data Index: 608391 (C4 (Web Text))

Max Activating Token Index: 975

Text #4

Max Range: 0.9684. Min Range: -0.9684

Max Act: 0.8199. Min Act: -0.0000

Data Index: 169381 (C4 (Web Text))

Max Activating Token Index: 789

Text #5

Max Range: 0.9684. Min Range: -0.9684

Max Act: 0.7947. Min Act: -0.0000

Data Index: 881771 (C4 (Web Text))

Max Activating Token Index: 630

Text #6

Max Range: 0.9684. Min Range: -0.9684

Max Act: 0.8073. Min Act: -0.0000

Data Index: 813244 (C4 (Web Text))

Max Activating Token Index: 551

Text #7

Max Range: 0.9684. Min Range: -0.9684

Max Act: 0.7817. Min Act: -0.0000

Data Index: 753850 (C4 (Web Text))

Max Activating Token Index: 534

Text #8

Max Range: 0.9684. Min Range: -0.9684

Max Act: 0.7768. Min Act: -0.0000

Data Index: 308871 (C4 (Web Text))

Max Activating Token Index: 809

Text #9

Max Range: 0.9684. Min Range: -0.9684

Max Act: 0.7619. Min Act: -0.0000

Data Index: 1357928 (C4 (Web Text))

Max Activating Token Index: 978

Text #10

Max Range: 0.9684. Min Range: -0.9684

Max Act: 0.7372. Min Act: -0.0000

Data Index: 1046492 (C4 (Web Text))

Max Activating Token Index: 473

Text #11

Max Range: 0.9684. Min Range: -0.9684

Max Act: 0.7170. Min Act: -0.0000

Data Index: 897865 (C4 (Web Text))

Max Activating Token Index: 167

Text #12

Max Range: 0.9684. Min Range: -0.9684

Max Act: 0.7293. Min Act: -0.0000

Data Index: 22739 (C4 (Web Text))

Max Activating Token Index: 398

Text #13

Max Range: 0.9684. Min Range: -0.9684

Max Act: 0.7560. Min Act: -0.0000

Data Index: 460588 (C4 (Web Text))

Max Activating Token Index: 882

Text #14

Max Range: 0.9684. Min Range: -0.9684

Max Act: 0.7327. Min Act: -0.0000

Data Index: 932998 (C4 (Web Text))

Max Activating Token Index: 285

Text #15

Max Range: 0.9684. Min Range: -0.9684

Max Act: 0.6998. Min Act: -0.0000

Data Index: 964526 (C4 (Web Text))

Max Activating Token Index: 452

Text #16

Max Range: 0.9684. Min Range: -0.9684

Max Act: 0.7158. Min Act: -0.0000

Data Index: 1195801 (C4 (Web Text))

Max Activating Token Index: 866

Text #17

Max Range: 0.9684. Min Range: -0.9684

Max Act: 0.6937. Min Act: -0.0000

Data Index: 77429 (C4 (Web Text))

Max Activating Token Index: 468

Text #18

Max Range: 0.9684. Min Range: -0.9684

Max Act: 0.7253. Min Act: -0.0000

Data Index: 134473 (C4 (Web Text))

Max Activating Token Index: 47

Text #19

Max Range: 0.9684. Min Range: -0.9684

Max Act: 0.6508. Min Act: -0.0000

Data Index: 698801 (C4 (Web Text))

Max Activating Token Index: 1004