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

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

Neuron 4800 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0711. Min Act: -0.0003

Data Index: 754572 (C4 (Web Text))

Max Activating Token Index: 199

Text #1

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0717. Min Act: -0.0003

Data Index: 65172 (C4 (Web Text))

Max Activating Token Index: 251

Text #2

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0662. Min Act: -0.0003

Data Index: 717528 (C4 (Web Text))

Max Activating Token Index: 342

Text #3

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0603. Min Act: -0.0003

Data Index: 524489 (C4 (Web Text))

Max Activating Token Index: 581

Text #4

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0544. Min Act: -0.0003

Data Index: 1172444 (C4 (Web Text))

Max Activating Token Index: 430

Text #5

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0535. Min Act: -0.0002

Data Index: 369747 (C4 (Web Text))

Max Activating Token Index: 811

Text #6

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0527. Min Act: -0.0003

Data Index: 998587 (C4 (Web Text))

Max Activating Token Index: 416

Text #7

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0503. Min Act: -0.0002

Data Index: 774855 (C4 (Web Text))

Max Activating Token Index: 868

Text #8

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0504. Min Act: -0.0003

Data Index: 1358944 (C4 (Web Text))

Max Activating Token Index: 954

Text #9

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0526. Min Act: -0.0003

Data Index: 150659 (C4 (Web Text))

Max Activating Token Index: 637

Text #10

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0481. Min Act: -0.0003

Data Index: 493316 (C4 (Web Text))

Max Activating Token Index: 206

Text #11

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0492. Min Act: -0.0003

Data Index: 38589 (C4 (Web Text))

Max Activating Token Index: 963

Text #12

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0490. Min Act: -0.0003

Data Index: 299925 (C4 (Web Text))

Max Activating Token Index: 560

Text #13

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0426. Min Act: -0.0003

Data Index: 385214 (C4 (Web Text))

Max Activating Token Index: 346

Text #14

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0398. Min Act: -0.0003

Data Index: 985793 (C4 (Web Text))

Max Activating Token Index: 10

Text #15

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0393. Min Act: -0.0003

Data Index: 941922 (C4 (Web Text))

Max Activating Token Index: 6

Text #16

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0381. Min Act: -0.0003

Data Index: 130976 (C4 (Web Text))

Max Activating Token Index: 34

Text #17

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0372. Min Act: -0.0003

Data Index: 387412 (C4 (Web Text))

Max Activating Token Index: 850

Text #18

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0340. Min Act: -0.0002

Data Index: 629484 (C4 (Web Text))

Max Activating Token Index: 185

Text #19

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0338. Min Act: -0.0002

Data Index: 727534 (C4 (Web Text))

Max Activating Token Index: 402