Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2462 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0888. Min Act: -0.0000

Data Index: 1180721 (C4 (Web Text))

Max Activating Token Index: 635

Text #1

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0748. Min Act: -0.0000

Data Index: 40556 (C4 (Web Text))

Max Activating Token Index: 147

Text #2

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0708. Min Act: -0.0001

Data Index: 1228518 (C4 (Web Text))

Max Activating Token Index: 92

Text #3

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0699. Min Act: -0.0001

Data Index: 741771 (C4 (Web Text))

Max Activating Token Index: 359

Text #4

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0694. Min Act: -0.0001

Data Index: 1257503 (C4 (Web Text))

Max Activating Token Index: 533

Text #5

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0670. Min Act: -0.0001

Data Index: 725459 (C4 (Web Text))

Max Activating Token Index: 937

Text #6

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0640. Min Act: -0.0001

Data Index: 391314 (C4 (Web Text))

Max Activating Token Index: 902

Text #7

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0710. Min Act: -0.0001

Data Index: 712657 (C4 (Web Text))

Max Activating Token Index: 532

Text #8

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0632. Min Act: -0.0001

Data Index: 605430 (C4 (Web Text))

Max Activating Token Index: 104

Text #9

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0593. Min Act: -0.0000

Data Index: 932788 (C4 (Web Text))

Max Activating Token Index: 432

Text #10

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0574. Min Act: -0.0001

Data Index: 957764 (C4 (Web Text))

Max Activating Token Index: 301

Text #11

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0623. Min Act: -0.0001

Data Index: 38507 (C4 (Web Text))

Max Activating Token Index: 138

Text #12

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0601. Min Act: -0.0001

Data Index: 377529 (C4 (Web Text))

Max Activating Token Index: 299

Text #13

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0611. Min Act: -0.0001

Data Index: 1296588 (C4 (Web Text))

Max Activating Token Index: 81

Text #14

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0517. Min Act: -0.0001

Data Index: 383162 (C4 (Web Text))

Max Activating Token Index: 539

Text #15

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0584. Min Act: -0.0001

Data Index: 1032369 (C4 (Web Text))

Max Activating Token Index: 794

Text #16

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0627. Min Act: -0.0000

Data Index: 520363 (C4 (Web Text))

Max Activating Token Index: 536

Text #17

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0561. Min Act: -0.0001

Data Index: 472013 (C4 (Web Text))

Max Activating Token Index: 407

Text #18

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0553. Min Act: -0.0001

Data Index: 873224 (C4 (Web Text))

Max Activating Token Index: 563

Text #19

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0547. Min Act: -0.0001

Data Index: 1468175 (Python Code)

Max Activating Token Index: 982