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

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

Neuron 11 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8398. Min Range: -1.8398

Max Act: 1.7016. Min Act: -0.0001

Data Index: 741093 (C4 (Web Text))

Max Activating Token Index: 797

Text #1

Max Range: 1.8398. Min Range: -1.8398

Max Act: 1.6210. Min Act: -0.0001

Data Index: 954965 (C4 (Web Text))

Max Activating Token Index: 32

Text #2

Max Range: 1.8398. Min Range: -1.8398

Max Act: 1.5889. Min Act: -0.0001

Data Index: 1358675 (C4 (Web Text))

Max Activating Token Index: 629

Text #3

Max Range: 1.8398. Min Range: -1.8398

Max Act: 1.4783. Min Act: -0.0001

Data Index: 605390 (C4 (Web Text))

Max Activating Token Index: 256

Text #4

Max Range: 1.8398. Min Range: -1.8398

Max Act: 1.8398. Min Act: -0.0001

Data Index: 642642 (C4 (Web Text))

Max Activating Token Index: 805

Text #5

Max Range: 1.8398. Min Range: -1.8398

Max Act: 1.6146. Min Act: -0.0001

Data Index: 300056 (C4 (Web Text))

Max Activating Token Index: 597

Text #6

Max Range: 1.8398. Min Range: -1.8398

Max Act: 1.4528. Min Act: -0.0001

Data Index: 672742 (C4 (Web Text))

Max Activating Token Index: 389

Text #7

Max Range: 1.8398. Min Range: -1.8398

Max Act: 1.5259. Min Act: -0.0001

Data Index: 1057248 (C4 (Web Text))

Max Activating Token Index: 155

Text #8

Max Range: 1.8398. Min Range: -1.8398

Max Act: 1.3595. Min Act: -0.0001

Data Index: 933550 (C4 (Web Text))

Max Activating Token Index: 769

Text #9

Max Range: 1.8398. Min Range: -1.8398

Max Act: 1.5910. Min Act: -0.0001

Data Index: 1008125 (C4 (Web Text))

Max Activating Token Index: 257

Text #10

Max Range: 1.8398. Min Range: -1.8398

Max Act: 1.5847. Min Act: -0.0001

Data Index: 665629 (C4 (Web Text))

Max Activating Token Index: 126

Text #11

Max Range: 1.8398. Min Range: -1.8398

Max Act: 1.2355. Min Act: -0.0001

Data Index: 618711 (C4 (Web Text))

Max Activating Token Index: 740

Text #12

Max Range: 1.8398. Min Range: -1.8398

Max Act: 1.4362. Min Act: -0.0001

Data Index: 1287909 (C4 (Web Text))

Max Activating Token Index: 950

Text #13

Max Range: 1.8398. Min Range: -1.8398

Max Act: 1.4036. Min Act: -0.0001

Data Index: 125307 (C4 (Web Text))

Max Activating Token Index: 20

Text #14

Max Range: 1.8398. Min Range: -1.8398

Max Act: 1.3669. Min Act: -0.0001

Data Index: 535600 (C4 (Web Text))

Max Activating Token Index: 890

Text #15

Max Range: 1.8398. Min Range: -1.8398

Max Act: 1.4243. Min Act: -0.0001

Data Index: 120638 (C4 (Web Text))

Max Activating Token Index: 217

Text #16

Max Range: 1.8398. Min Range: -1.8398

Max Act: 1.3659. Min Act: -0.0001

Data Index: 443755 (C4 (Web Text))

Max Activating Token Index: 792

Text #17

Max Range: 1.8398. Min Range: -1.8398

Max Act: 1.2998. Min Act: -0.0001

Data Index: 434462 (C4 (Web Text))

Max Activating Token Index: 70

Text #18

Max Range: 1.8398. Min Range: -1.8398

Max Act: 1.2747. Min Act: -0.0001

Data Index: 761415 (C4 (Web Text))

Max Activating Token Index: 143

Text #19

Max Range: 1.8398. Min Range: -1.8398

Max Act: 1.2392. Min Act: -0.0001

Data Index: 235544 (C4 (Web Text))

Max Activating Token Index: 378