Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3886 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5379. Min Range: -0.5379

Max Act: 0.5379. Min Act: -0.0000

Data Index: 1291532 (C4 (Web Text))

Max Activating Token Index: 504

Text #1

Max Range: 0.5379. Min Range: -0.5379

Max Act: 0.4258. Min Act: -0.0000

Data Index: 373849 (C4 (Web Text))

Max Activating Token Index: 29

Text #2

Max Range: 0.5379. Min Range: -0.5379

Max Act: 0.3372. Min Act: -0.0000

Data Index: 1331115 (C4 (Web Text))

Max Activating Token Index: 80

Text #3

Max Range: 0.5379. Min Range: -0.5379

Max Act: 0.3265. Min Act: -0.0000

Data Index: 9815 (C4 (Web Text))

Max Activating Token Index: 781

Text #4

Max Range: 0.5379. Min Range: -0.5379

Max Act: 0.3328. Min Act: -0.0000

Data Index: 303074 (C4 (Web Text))

Max Activating Token Index: 231

Text #5

Max Range: 0.5379. Min Range: -0.5379

Max Act: 0.3014. Min Act: -0.0000

Data Index: 294611 (C4 (Web Text))

Max Activating Token Index: 617

Text #6

Max Range: 0.5379. Min Range: -0.5379

Max Act: 0.2800. Min Act: -0.0000

Data Index: 215443 (C4 (Web Text))

Max Activating Token Index: 296

Text #7

Max Range: 0.5379. Min Range: -0.5379

Max Act: 0.2690. Min Act: -0.0000

Data Index: 10311 (C4 (Web Text))

Max Activating Token Index: 661

Text #8

Max Range: 0.5379. Min Range: -0.5379

Max Act: 0.3098. Min Act: -0.0000

Data Index: 1024415 (C4 (Web Text))

Max Activating Token Index: 308

Text #9

Max Range: 0.5379. Min Range: -0.5379

Max Act: 0.3025. Min Act: -0.0000

Data Index: 704852 (C4 (Web Text))

Max Activating Token Index: 250

Text #10

Max Range: 0.5379. Min Range: -0.5379

Max Act: 0.2551. Min Act: -0.0000

Data Index: 745317 (C4 (Web Text))

Max Activating Token Index: 472

Text #11

Max Range: 0.5379. Min Range: -0.5379

Max Act: 0.2570. Min Act: -0.0000

Data Index: 736977 (C4 (Web Text))

Max Activating Token Index: 856

Text #12

Max Range: 0.5379. Min Range: -0.5379

Max Act: 0.2474. Min Act: -0.0000

Data Index: 1074096 (C4 (Web Text))

Max Activating Token Index: 884

Text #13

Max Range: 0.5379. Min Range: -0.5379

Max Act: 0.2446. Min Act: -0.0000

Data Index: 470792 (C4 (Web Text))

Max Activating Token Index: 82

Text #14

Max Range: 0.5379. Min Range: -0.5379

Max Act: 0.2608. Min Act: -0.0000

Data Index: 757626 (C4 (Web Text))

Max Activating Token Index: 707

Text #15

Max Range: 0.5379. Min Range: -0.5379

Max Act: 0.2389. Min Act: -0.0000

Data Index: 301577 (C4 (Web Text))

Max Activating Token Index: 376

Text #16

Max Range: 0.5379. Min Range: -0.5379

Max Act: 0.2498. Min Act: -0.0000

Data Index: 81606 (C4 (Web Text))

Max Activating Token Index: 855

Text #17

Max Range: 0.5379. Min Range: -0.5379

Max Act: 0.2138. Min Act: -0.0000

Data Index: 86844 (C4 (Web Text))

Max Activating Token Index: 461

Text #18

Max Range: 0.5379. Min Range: -0.5379

Max Act: 0.2211. Min Act: -0.0000

Data Index: 623816 (C4 (Web Text))

Max Activating Token Index: 999

Text #19

Max Range: 0.5379. Min Range: -0.5379

Max Act: 0.2421. Min Act: -0.0000

Data Index: 1186796 (C4 (Web Text))

Max Activating Token Index: 788