Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3184 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0745. Min Act: -0.0001

Data Index: 256089 (C4 (Web Text))

Max Activating Token Index: 558

Text #1

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0734. Min Act: -0.0000

Data Index: 1159761 (C4 (Web Text))

Max Activating Token Index: 943

Text #2

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0651. Min Act: -0.0000

Data Index: 829169 (C4 (Web Text))

Max Activating Token Index: 620

Text #3

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0615. Min Act: -0.0001

Data Index: 331043 (C4 (Web Text))

Max Activating Token Index: 116

Text #4

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0631. Min Act: -0.0000

Data Index: 438482 (C4 (Web Text))

Max Activating Token Index: 834

Text #5

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0559. Min Act: -0.0001

Data Index: 216721 (C4 (Web Text))

Max Activating Token Index: 197

Text #6

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0555. Min Act: -0.0000

Data Index: 1321680 (C4 (Web Text))

Max Activating Token Index: 961

Text #7

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0541. Min Act: -0.0001

Data Index: 1257970 (C4 (Web Text))

Max Activating Token Index: 300

Text #8

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0577. Min Act: -0.0000

Data Index: 1277716 (C4 (Web Text))

Max Activating Token Index: 736

Text #9

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0553. Min Act: -0.0001

Data Index: 202817 (C4 (Web Text))

Max Activating Token Index: 855

Text #10

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0532. Min Act: -0.0001

Data Index: 147323 (C4 (Web Text))

Max Activating Token Index: 534

Text #11

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0532. Min Act: -0.0001

Data Index: 1222256 (C4 (Web Text))

Max Activating Token Index: 740

Text #12

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0511. Min Act: -0.0001

Data Index: 686152 (C4 (Web Text))

Max Activating Token Index: 642

Text #13

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0545. Min Act: -0.0001

Data Index: 561323 (C4 (Web Text))

Max Activating Token Index: 342

Text #14

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0522. Min Act: -0.0000

Data Index: 950331 (C4 (Web Text))

Max Activating Token Index: 675

Text #15

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0500. Min Act: -0.0001

Data Index: 985815 (C4 (Web Text))

Max Activating Token Index: 123

Text #16

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0543. Min Act: -0.0001

Data Index: 500336 (C4 (Web Text))

Max Activating Token Index: 852

Text #17

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0517. Min Act: -0.0001

Data Index: 237220 (C4 (Web Text))

Max Activating Token Index: 304

Text #18

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0498. Min Act: -0.0001

Data Index: 968807 (C4 (Web Text))

Max Activating Token Index: 320

Text #19

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0534. Min Act: -0.0001

Data Index: 274246 (C4 (Web Text))

Max Activating Token Index: 233