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

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

Neuron 4549 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7434. Min Range: -4.7434

Max Act: 4.7434. Min Act: -0.0000

Data Index: 410555 (C4 (Web Text))

Max Activating Token Index: 737

Text #1

Max Range: 4.7434. Min Range: -4.7434

Max Act: 4.4201. Min Act: -0.0000

Data Index: 926628 (C4 (Web Text))

Max Activating Token Index: 695

Text #2

Max Range: 4.7434. Min Range: -4.7434

Max Act: 4.4000. Min Act: -0.0000

Data Index: 94647 (C4 (Web Text))

Max Activating Token Index: 853

Text #3

Max Range: 4.7434. Min Range: -4.7434

Max Act: 4.7043. Min Act: -0.0000

Data Index: 853404 (C4 (Web Text))

Max Activating Token Index: 104

Text #4

Max Range: 4.7434. Min Range: -4.7434

Max Act: 4.1180. Min Act: -0.0000

Data Index: 501703 (C4 (Web Text))

Max Activating Token Index: 342

Text #5

Max Range: 4.7434. Min Range: -4.7434

Max Act: 4.2280. Min Act: -0.0000

Data Index: 137579 (C4 (Web Text))

Max Activating Token Index: 639

Text #6

Max Range: 4.7434. Min Range: -4.7434

Max Act: 4.2010. Min Act: -0.0000

Data Index: 93927 (C4 (Web Text))

Max Activating Token Index: 685

Text #7

Max Range: 4.7434. Min Range: -4.7434

Max Act: 3.9542. Min Act: -0.0000

Data Index: 671000 (C4 (Web Text))

Max Activating Token Index: 933

Text #8

Max Range: 4.7434. Min Range: -4.7434

Max Act: 4.3055. Min Act: -0.0000

Data Index: 783851 (C4 (Web Text))

Max Activating Token Index: 297

Text #9

Max Range: 4.7434. Min Range: -4.7434

Max Act: 4.1993. Min Act: -0.0000

Data Index: 602293 (C4 (Web Text))

Max Activating Token Index: 952

Text #10

Max Range: 4.7434. Min Range: -4.7434

Max Act: 4.1584. Min Act: -0.0000

Data Index: 358509 (C4 (Web Text))

Max Activating Token Index: 632

Text #11

Max Range: 4.7434. Min Range: -4.7434

Max Act: 3.5553. Min Act: -0.0000

Data Index: 410935 (C4 (Web Text))

Max Activating Token Index: 844

Text #12

Max Range: 4.7434. Min Range: -4.7434

Max Act: 3.8001. Min Act: -0.0000

Data Index: 721701 (C4 (Web Text))

Max Activating Token Index: 437

Text #13

Max Range: 4.7434. Min Range: -4.7434

Max Act: 3.9358. Min Act: -0.0000

Data Index: 128672 (C4 (Web Text))

Max Activating Token Index: 972

Text #14

Max Range: 4.7434. Min Range: -4.7434

Max Act: 3.5926. Min Act: -0.0000

Data Index: 710505 (C4 (Web Text))

Max Activating Token Index: 631

Text #15

Max Range: 4.7434. Min Range: -4.7434

Max Act: 3.7575. Min Act: -0.0000

Data Index: 757256 (C4 (Web Text))

Max Activating Token Index: 151

Text #16

Max Range: 4.7434. Min Range: -4.7434

Max Act: 3.8153. Min Act: -0.0000

Data Index: 554495 (C4 (Web Text))

Max Activating Token Index: 661

Text #17

Max Range: 4.7434. Min Range: -4.7434

Max Act: 3.6625. Min Act: -0.0000

Data Index: 881306 (C4 (Web Text))

Max Activating Token Index: 314

Text #18

Max Range: 4.7434. Min Range: -4.7434

Max Act: 3.3104. Min Act: -0.0000

Data Index: 313162 (C4 (Web Text))

Max Activating Token Index: 329

Text #19

Max Range: 4.7434. Min Range: -4.7434

Max Act: 3.4638. Min Act: -0.0000

Data Index: 512224 (C4 (Web Text))

Max Activating Token Index: 556