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

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

Neuron 386 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4385. Min Range: -3.4385

Max Act: 3.4385. Min Act: -0.0000

Data Index: 1348781 (C4 (Web Text))

Max Activating Token Index: 886

Text #1

Max Range: 3.4385. Min Range: -3.4385

Max Act: 3.3104. Min Act: -0.0000

Data Index: 21045 (C4 (Web Text))

Max Activating Token Index: 192

Text #2

Max Range: 3.4385. Min Range: -3.4385

Max Act: 2.9029. Min Act: -0.0000

Data Index: 302241 (C4 (Web Text))

Max Activating Token Index: 254

Text #3

Max Range: 3.4385. Min Range: -3.4385

Max Act: 2.8479. Min Act: -0.0000

Data Index: 713616 (C4 (Web Text))

Max Activating Token Index: 909

Text #4

Max Range: 3.4385. Min Range: -3.4385

Max Act: 2.7797. Min Act: -0.0000

Data Index: 169648 (C4 (Web Text))

Max Activating Token Index: 526

Text #5

Max Range: 3.4385. Min Range: -3.4385

Max Act: 2.6347. Min Act: -0.0000

Data Index: 989257 (C4 (Web Text))

Max Activating Token Index: 407

Text #6

Max Range: 3.4385. Min Range: -3.4385

Max Act: 2.8501. Min Act: -0.0000

Data Index: 1185730 (C4 (Web Text))

Max Activating Token Index: 634

Text #7

Max Range: 3.4385. Min Range: -3.4385

Max Act: 2.7000. Min Act: -0.0000

Data Index: 1009810 (C4 (Web Text))

Max Activating Token Index: 45

Text #8

Max Range: 3.4385. Min Range: -3.4385

Max Act: 2.7637. Min Act: -0.0000

Data Index: 252349 (C4 (Web Text))

Max Activating Token Index: 205

Text #9

Max Range: 3.4385. Min Range: -3.4385

Max Act: 2.6317. Min Act: -0.0000

Data Index: 119071 (C4 (Web Text))

Max Activating Token Index: 409

Text #10

Max Range: 3.4385. Min Range: -3.4385

Max Act: 2.6297. Min Act: -0.0000

Data Index: 711607 (C4 (Web Text))

Max Activating Token Index: 314

Text #11

Max Range: 3.4385. Min Range: -3.4385

Max Act: 2.6401. Min Act: -0.0000

Data Index: 358392 (C4 (Web Text))

Max Activating Token Index: 338

Text #12

Max Range: 3.4385. Min Range: -3.4385

Max Act: 2.4904. Min Act: -0.0000

Data Index: 1337064 (C4 (Web Text))

Max Activating Token Index: 507

Text #13

Max Range: 3.4385. Min Range: -3.4385

Max Act: 2.7360. Min Act: -0.0000

Data Index: 1181180 (C4 (Web Text))

Max Activating Token Index: 1008

Text #14

Max Range: 3.4385. Min Range: -3.4385

Max Act: 2.5956. Min Act: -0.0000

Data Index: 789276 (C4 (Web Text))

Max Activating Token Index: 604

Text #15

Max Range: 3.4385. Min Range: -3.4385

Max Act: 2.3906. Min Act: -0.0000

Data Index: 1010717 (C4 (Web Text))

Max Activating Token Index: 913

Text #16

Max Range: 3.4385. Min Range: -3.4385

Max Act: 2.6190. Min Act: -0.0000

Data Index: 195810 (C4 (Web Text))

Max Activating Token Index: 208

Text #17

Max Range: 3.4385. Min Range: -3.4385

Max Act: 2.5007. Min Act: -0.0000

Data Index: 456214 (C4 (Web Text))

Max Activating Token Index: 409

Text #18

Max Range: 3.4385. Min Range: -3.4385

Max Act: 2.5723. Min Act: -0.0000

Data Index: 16032 (C4 (Web Text))

Max Activating Token Index: 743

Text #19

Max Range: 3.4385. Min Range: -3.4385

Max Act: 2.4482. Min Act: -0.0000

Data Index: 561775 (C4 (Web Text))

Max Activating Token Index: 737