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

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

Neuron 4950 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9639. Min Range: -0.9639

Max Act: 0.9137. Min Act: -0.0000

Data Index: 139559 (C4 (Web Text))

Max Activating Token Index: 921

Text #1

Max Range: 0.9639. Min Range: -0.9639

Max Act: 0.9615. Min Act: -0.0000

Data Index: 358760 (C4 (Web Text))

Max Activating Token Index: 625

Text #2

Max Range: 0.9639. Min Range: -0.9639

Max Act: 0.9019. Min Act: -0.0000

Data Index: 481830 (C4 (Web Text))

Max Activating Token Index: 322

Text #3

Max Range: 0.9639. Min Range: -0.9639

Max Act: 0.9590. Min Act: -0.0000

Data Index: 324899 (C4 (Web Text))

Max Activating Token Index: 818

Text #4

Max Range: 0.9639. Min Range: -0.9639

Max Act: 0.9625. Min Act: -0.0000

Data Index: 663496 (C4 (Web Text))

Max Activating Token Index: 484

Text #5

Max Range: 0.9639. Min Range: -0.9639

Max Act: 0.9154. Min Act: -0.0000

Data Index: 445590 (C4 (Web Text))

Max Activating Token Index: 1003

Text #6

Max Range: 0.9639. Min Range: -0.9639

Max Act: 0.9028. Min Act: -0.0000

Data Index: 806230 (C4 (Web Text))

Max Activating Token Index: 80

Text #7

Max Range: 0.9639. Min Range: -0.9639

Max Act: 0.9639. Min Act: -0.0000

Data Index: 1588428 (Python Code)

Max Activating Token Index: 982

Text #8

Max Range: 0.9639. Min Range: -0.9639

Max Act: 0.8603. Min Act: -0.0000

Data Index: 620736 (C4 (Web Text))

Max Activating Token Index: 53

Text #9

Max Range: 0.9639. Min Range: -0.9639

Max Act: 0.9087. Min Act: -0.0000

Data Index: 1051499 (C4 (Web Text))

Max Activating Token Index: 779

Text #10

Max Range: 0.9639. Min Range: -0.9639

Max Act: 0.9056. Min Act: -0.0000

Data Index: 259609 (C4 (Web Text))

Max Activating Token Index: 462

Text #11

Max Range: 0.9639. Min Range: -0.9639

Max Act: 0.9182. Min Act: -0.0000

Data Index: 315251 (C4 (Web Text))

Max Activating Token Index: 98

Text #12

Max Range: 0.9639. Min Range: -0.9639

Max Act: 0.8825. Min Act: -0.0000

Data Index: 398758 (C4 (Web Text))

Max Activating Token Index: 373

Text #13

Max Range: 0.9639. Min Range: -0.9639

Max Act: 0.8749. Min Act: -0.0000

Data Index: 1260430 (C4 (Web Text))

Max Activating Token Index: 576

Text #14

Max Range: 0.9639. Min Range: -0.9639

Max Act: 0.8311. Min Act: -0.0000

Data Index: 1267503 (C4 (Web Text))

Max Activating Token Index: 295

Text #15

Max Range: 0.9639. Min Range: -0.9639

Max Act: 0.9593. Min Act: -0.0000

Data Index: 1277695 (C4 (Web Text))

Max Activating Token Index: 1009

Text #16

Max Range: 0.9639. Min Range: -0.9639

Max Act: 0.8630. Min Act: -0.0000

Data Index: 1010342 (C4 (Web Text))

Max Activating Token Index: 716

Text #17

Max Range: 0.9639. Min Range: -0.9639

Max Act: 0.8690. Min Act: -0.0000

Data Index: 219018 (C4 (Web Text))

Max Activating Token Index: 410

Text #18

Max Range: 0.9639. Min Range: -0.9639

Max Act: 0.8867. Min Act: -0.0000

Data Index: 637176 (C4 (Web Text))

Max Activating Token Index: 838

Text #19

Max Range: 0.9639. Min Range: -0.9639

Max Act: 0.9398. Min Act: -0.0000

Data Index: 137852 (C4 (Web Text))

Max Activating Token Index: 439