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

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

Neuron 2575 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5498. Min Range: -0.5498

Max Act: 0.5498. Min Act: -0.0000

Data Index: 1000794 (C4 (Web Text))

Max Activating Token Index: 739

Text #1

Max Range: 0.5498. Min Range: -0.5498

Max Act: 0.4262. Min Act: -0.0000

Data Index: 408891 (C4 (Web Text))

Max Activating Token Index: 971

Text #2

Max Range: 0.5498. Min Range: -0.5498

Max Act: 0.4220. Min Act: -0.0000

Data Index: 1069345 (C4 (Web Text))

Max Activating Token Index: 580

Text #3

Max Range: 0.5498. Min Range: -0.5498

Max Act: 0.4156. Min Act: -0.0000

Data Index: 914255 (C4 (Web Text))

Max Activating Token Index: 992

Text #4

Max Range: 0.5498. Min Range: -0.5498

Max Act: 0.4167. Min Act: -0.0000

Data Index: 428523 (C4 (Web Text))

Max Activating Token Index: 528

Text #5

Max Range: 0.5498. Min Range: -0.5498

Max Act: 0.4157. Min Act: -0.0000

Data Index: 464588 (C4 (Web Text))

Max Activating Token Index: 374

Text #6

Max Range: 0.5498. Min Range: -0.5498

Max Act: 0.3958. Min Act: -0.0000

Data Index: 544342 (C4 (Web Text))

Max Activating Token Index: 779

Text #7

Max Range: 0.5498. Min Range: -0.5498

Max Act: 0.3706. Min Act: -0.0000

Data Index: 263539 (C4 (Web Text))

Max Activating Token Index: 726

Text #8

Max Range: 0.5498. Min Range: -0.5498

Max Act: 0.3969. Min Act: -0.0000

Data Index: 527525 (C4 (Web Text))

Max Activating Token Index: 700

Text #9

Max Range: 0.5498. Min Range: -0.5498

Max Act: 0.3920. Min Act: -0.0000

Data Index: 907654 (C4 (Web Text))

Max Activating Token Index: 891

Text #10

Max Range: 0.5498. Min Range: -0.5498

Max Act: 0.3823. Min Act: -0.0000

Data Index: 301334 (C4 (Web Text))

Max Activating Token Index: 596

Text #11

Max Range: 0.5498. Min Range: -0.5498

Max Act: 0.3779. Min Act: -0.0000

Data Index: 45741 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.5498. Min Range: -0.5498

Max Act: 0.3708. Min Act: -0.0000

Data Index: 861904 (C4 (Web Text))

Max Activating Token Index: 630

Text #13

Max Range: 0.5498. Min Range: -0.5498

Max Act: 0.3463. Min Act: -0.0000

Data Index: 480179 (C4 (Web Text))

Max Activating Token Index: 578

Text #14

Max Range: 0.5498. Min Range: -0.5498

Max Act: 0.3525. Min Act: -0.0000

Data Index: 1113262 (C4 (Web Text))

Max Activating Token Index: 675

Text #15

Max Range: 0.5498. Min Range: -0.5498

Max Act: 0.3404. Min Act: -0.0000

Data Index: 1351540 (C4 (Web Text))

Max Activating Token Index: 188

Text #16

Max Range: 0.5498. Min Range: -0.5498

Max Act: 0.3504. Min Act: -0.0000

Data Index: 992688 (C4 (Web Text))

Max Activating Token Index: 933

Text #17

Max Range: 0.5498. Min Range: -0.5498

Max Act: 0.3500. Min Act: -0.0000

Data Index: 510480 (C4 (Web Text))

Max Activating Token Index: 370

Text #18

Max Range: 0.5498. Min Range: -0.5498

Max Act: 0.3562. Min Act: -0.0000

Data Index: 425321 (C4 (Web Text))

Max Activating Token Index: 936

Text #19

Max Range: 0.5498. Min Range: -0.5498

Max Act: 0.3340. Min Act: -0.0000

Data Index: 179968 (C4 (Web Text))

Max Activating Token Index: 412