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

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

Neuron 3646 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: 0.0651. Min Range: -0.0651

Max Act: 0.0650. Min Act: -0.0000

Data Index: 306065 (C4 (Web Text))

Max Activating Token Index: 408

Text #1

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0651. Min Act: -0.0000

Data Index: 1300198 (C4 (Web Text))

Max Activating Token Index: 303

Text #2

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0620. Min Act: -0.0000

Data Index: 91636 (C4 (Web Text))

Max Activating Token Index: 360

Text #3

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0634. Min Act: -0.0000

Data Index: 979355 (C4 (Web Text))

Max Activating Token Index: 825

Text #4

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0587. Min Act: -0.0000

Data Index: 380080 (C4 (Web Text))

Max Activating Token Index: 598

Text #5

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0590. Min Act: -0.0000

Data Index: 655181 (C4 (Web Text))

Max Activating Token Index: 776

Text #6

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0579. Min Act: -0.0000

Data Index: 326126 (C4 (Web Text))

Max Activating Token Index: 571

Text #7

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0589. Min Act: -0.0000

Data Index: 673732 (C4 (Web Text))

Max Activating Token Index: 55

Text #8

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0556. Min Act: -0.0000

Data Index: 1389217 (Python Code)

Max Activating Token Index: 677

Text #9

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0553. Min Act: -0.0000

Data Index: 1193788 (C4 (Web Text))

Max Activating Token Index: 415

Text #10

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0559. Min Act: -0.0000

Data Index: 632623 (C4 (Web Text))

Max Activating Token Index: 232

Text #11

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0503. Min Act: -0.0000

Data Index: 1184110 (C4 (Web Text))

Max Activating Token Index: 510

Text #12

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0492. Min Act: -0.0000

Data Index: 731633 (C4 (Web Text))

Max Activating Token Index: 414

Text #13

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0542. Min Act: -0.0000

Data Index: 1314893 (C4 (Web Text))

Max Activating Token Index: 176

Text #14

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0500. Min Act: -0.0000

Data Index: 388375 (C4 (Web Text))

Max Activating Token Index: 897

Text #15

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0493. Min Act: -0.0000

Data Index: 699659 (C4 (Web Text))

Max Activating Token Index: 917

Text #16

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0524. Min Act: -0.0000

Data Index: 1128835 (C4 (Web Text))

Max Activating Token Index: 604

Text #17

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0507. Min Act: -0.0000

Data Index: 1575517 (Python Code)

Max Activating Token Index: 92

Text #18

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0504. Min Act: -0.0000

Data Index: 831066 (C4 (Web Text))

Max Activating Token Index: 941

Text #19

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0503. Min Act: -0.0000

Data Index: 620956 (C4 (Web Text))

Max Activating Token Index: 277