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

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

Neuron 3253 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.2464. Min Range: -6.2464

Max Act: 5.9169. Min Act: -0.0000

Data Index: 348974 (C4 (Web Text))

Max Activating Token Index: 48

Text #1

Max Range: 6.2464. Min Range: -6.2464

Max Act: 5.7783. Min Act: -0.0000

Data Index: 706315 (C4 (Web Text))

Max Activating Token Index: 630

Text #2

Max Range: 6.2464. Min Range: -6.2464

Max Act: 5.3623. Min Act: -0.0000

Data Index: 357880 (C4 (Web Text))

Max Activating Token Index: 376

Text #3

Max Range: 6.2464. Min Range: -6.2464

Max Act: 5.1454. Min Act: -0.0000

Data Index: 212660 (C4 (Web Text))

Max Activating Token Index: 396

Text #4

Max Range: 6.2464. Min Range: -6.2464

Max Act: 5.2941. Min Act: 0.0000

Data Index: 399845 (C4 (Web Text))

Max Activating Token Index: 651

Text #5

Max Range: 6.2464. Min Range: -6.2464

Max Act: 5.4596. Min Act: -0.0000

Data Index: 510101 (C4 (Web Text))

Max Activating Token Index: 254

Text #6

Max Range: 6.2464. Min Range: -6.2464

Max Act: 5.2721. Min Act: 0.0000

Data Index: 381584 (C4 (Web Text))

Max Activating Token Index: 665

Text #7

Max Range: 6.2464. Min Range: -6.2464

Max Act: 6.2464. Min Act: 0.0000

Data Index: 702168 (C4 (Web Text))

Max Activating Token Index: 266

Text #8

Max Range: 6.2464. Min Range: -6.2464

Max Act: 5.1348. Min Act: -0.0000

Data Index: 1318839 (C4 (Web Text))

Max Activating Token Index: 295

Text #9

Max Range: 6.2464. Min Range: -6.2464

Max Act: 5.1740. Min Act: 0.0000

Data Index: 672913 (C4 (Web Text))

Max Activating Token Index: 564

Text #10

Max Range: 6.2464. Min Range: -6.2464

Max Act: 5.3417. Min Act: -0.0000

Data Index: 960194 (C4 (Web Text))

Max Activating Token Index: 640

Text #11

Max Range: 6.2464. Min Range: -6.2464

Max Act: 5.5097. Min Act: 0.0000

Data Index: 232753 (C4 (Web Text))

Max Activating Token Index: 371

Text #12

Max Range: 6.2464. Min Range: -6.2464

Max Act: 5.0440. Min Act: 0.0000

Data Index: 222463 (C4 (Web Text))

Max Activating Token Index: 321

Text #13

Max Range: 6.2464. Min Range: -6.2464

Max Act: 5.0049. Min Act: 0.0000

Data Index: 993813 (C4 (Web Text))

Max Activating Token Index: 618

Text #14

Max Range: 6.2464. Min Range: -6.2464

Max Act: 5.0328. Min Act: -0.0000

Data Index: 400110 (C4 (Web Text))

Max Activating Token Index: 450

Text #15

Max Range: 6.2464. Min Range: -6.2464

Max Act: 5.0057. Min Act: -0.0000

Data Index: 828218 (C4 (Web Text))

Max Activating Token Index: 464

Text #16

Max Range: 6.2464. Min Range: -6.2464

Max Act: 5.1444. Min Act: -0.0000

Data Index: 1099010 (C4 (Web Text))

Max Activating Token Index: 683

Text #17

Max Range: 6.2464. Min Range: -6.2464

Max Act: 5.3414. Min Act: -0.0000

Data Index: 640150 (C4 (Web Text))

Max Activating Token Index: 369

Text #18

Max Range: 6.2464. Min Range: -6.2464

Max Act: 5.0384. Min Act: -0.0000

Data Index: 940842 (C4 (Web Text))

Max Activating Token Index: 782

Text #19

Max Range: 6.2464. Min Range: -6.2464

Max Act: 4.8409. Min Act: -0.0000

Data Index: 654326 (C4 (Web Text))

Max Activating Token Index: 470