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

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

Neuron 1653 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.8476. Min Act: -0.0000

Data Index: 618877 (C4 (Web Text))

Max Activating Token Index: 836

Text #1

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.6496. Min Act: -0.0000

Data Index: 170621 (C4 (Web Text))

Max Activating Token Index: 695

Text #2

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.3707. Min Act: -0.0000

Data Index: 1136498 (C4 (Web Text))

Max Activating Token Index: 496

Text #3

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.2230. Min Act: -0.0000

Data Index: 1224972 (C4 (Web Text))

Max Activating Token Index: 400

Text #4

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.2747. Min Act: -0.0000

Data Index: 474881 (C4 (Web Text))

Max Activating Token Index: 74

Text #5

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.2895. Min Act: -0.0000

Data Index: 439440 (C4 (Web Text))

Max Activating Token Index: 282

Text #6

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.3067. Min Act: -0.0000

Data Index: 1288681 (C4 (Web Text))

Max Activating Token Index: 800

Text #7

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.2069. Min Act: -0.0000

Data Index: 724047 (C4 (Web Text))

Max Activating Token Index: 710

Text #8

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.1522. Min Act: -0.0000

Data Index: 957354 (C4 (Web Text))

Max Activating Token Index: 50

Text #9

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.2467. Min Act: -0.0000

Data Index: 184484 (C4 (Web Text))

Max Activating Token Index: 640

Text #10

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.1356. Min Act: -0.0000

Data Index: 1345955 (C4 (Web Text))

Max Activating Token Index: 390

Text #11

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.1867. Min Act: -0.0000

Data Index: 1247680 (C4 (Web Text))

Max Activating Token Index: 191

Text #12

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.1455. Min Act: -0.0000

Data Index: 913021 (C4 (Web Text))

Max Activating Token Index: 663

Text #13

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.1478. Min Act: -0.0000

Data Index: 741914 (C4 (Web Text))

Max Activating Token Index: 938

Text #14

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.1072. Min Act: -0.0000

Data Index: 1265038 (C4 (Web Text))

Max Activating Token Index: 1007

Text #15

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.0615. Min Act: -0.0000

Data Index: 412100 (C4 (Web Text))

Max Activating Token Index: 655

Text #16

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.1614. Min Act: -0.0000

Data Index: 472668 (C4 (Web Text))

Max Activating Token Index: 217

Text #17

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.1024. Min Act: -0.0000

Data Index: 1080755 (C4 (Web Text))

Max Activating Token Index: 138

Text #18

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.0910. Min Act: -0.0000

Data Index: 221724 (C4 (Web Text))

Max Activating Token Index: 909

Text #19

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.1324. Min Act: -0.0000

Data Index: 593959 (C4 (Web Text))

Max Activating Token Index: 677