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

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

Neuron 1279 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0932. Min Range: -0.0932

Max Act: 0.0932. Min Act: -0.0002

Data Index: 6766 (C4 (Web Text))

Max Activating Token Index: 900

Text #1

Max Range: 0.0932. Min Range: -0.0932

Max Act: 0.0802. Min Act: -0.0002

Data Index: 1092970 (C4 (Web Text))

Max Activating Token Index: 398

Text #2

Max Range: 0.0932. Min Range: -0.0932

Max Act: 0.0649. Min Act: -0.0002

Data Index: 823268 (C4 (Web Text))

Max Activating Token Index: 344

Text #3

Max Range: 0.0932. Min Range: -0.0932

Max Act: 0.0709. Min Act: -0.0002

Data Index: 173078 (C4 (Web Text))

Max Activating Token Index: 745

Text #4

Max Range: 0.0932. Min Range: -0.0932

Max Act: 0.0754. Min Act: -0.0002

Data Index: 27964 (C4 (Web Text))

Max Activating Token Index: 879

Text #5

Max Range: 0.0932. Min Range: -0.0932

Max Act: 0.0698. Min Act: -0.0002

Data Index: 59162 (C4 (Web Text))

Max Activating Token Index: 250

Text #6

Max Range: 0.0932. Min Range: -0.0932

Max Act: 0.0658. Min Act: -0.0002

Data Index: 1044464 (C4 (Web Text))

Max Activating Token Index: 330

Text #7

Max Range: 0.0932. Min Range: -0.0932

Max Act: 0.0723. Min Act: -0.0002

Data Index: 891139 (C4 (Web Text))

Max Activating Token Index: 1016

Text #8

Max Range: 0.0932. Min Range: -0.0932

Max Act: 0.0660. Min Act: -0.0002

Data Index: 349308 (C4 (Web Text))

Max Activating Token Index: 22

Text #9

Max Range: 0.0932. Min Range: -0.0932

Max Act: 0.0677. Min Act: -0.0002

Data Index: 602305 (C4 (Web Text))

Max Activating Token Index: 387

Text #10

Max Range: 0.0932. Min Range: -0.0932

Max Act: 0.0514. Min Act: -0.0002

Data Index: 82622 (C4 (Web Text))

Max Activating Token Index: 196

Text #11

Max Range: 0.0932. Min Range: -0.0932

Max Act: 0.0666. Min Act: -0.0002

Data Index: 537541 (C4 (Web Text))

Max Activating Token Index: 732

Text #12

Max Range: 0.0932. Min Range: -0.0932

Max Act: 0.0582. Min Act: -0.0002

Data Index: 638902 (C4 (Web Text))

Max Activating Token Index: 1004

Text #13

Max Range: 0.0932. Min Range: -0.0932

Max Act: 0.0595. Min Act: -0.0002

Data Index: 239112 (C4 (Web Text))

Max Activating Token Index: 610

Text #14

Max Range: 0.0932. Min Range: -0.0932

Max Act: 0.0617. Min Act: -0.0002

Data Index: 652695 (C4 (Web Text))

Max Activating Token Index: 516

Text #15

Max Range: 0.0932. Min Range: -0.0932

Max Act: 0.0605. Min Act: -0.0002

Data Index: 1082412 (C4 (Web Text))

Max Activating Token Index: 102

Text #16

Max Range: 0.0932. Min Range: -0.0932

Max Act: 0.0562. Min Act: -0.0002

Data Index: 173092 (C4 (Web Text))

Max Activating Token Index: 894

Text #17

Max Range: 0.0932. Min Range: -0.0932

Max Act: 0.0600. Min Act: -0.0002

Data Index: 1276091 (C4 (Web Text))

Max Activating Token Index: 918

Text #18

Max Range: 0.0932. Min Range: -0.0932

Max Act: 0.0519. Min Act: -0.0002

Data Index: 777906 (C4 (Web Text))

Max Activating Token Index: 226

Text #19

Max Range: 0.0932. Min Range: -0.0932

Max Act: 0.0572. Min Act: -0.0002

Data Index: 408419 (C4 (Web Text))

Max Activating Token Index: 12