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

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

Neuron 1834 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4622. Min Range: -1.4622

Max Act: 1.4622. Min Act: -0.0001

Data Index: 836726 (C4 (Web Text))

Max Activating Token Index: 748

Text #1

Max Range: 1.4622. Min Range: -1.4622

Max Act: 1.3384. Min Act: -0.0001

Data Index: 345323 (C4 (Web Text))

Max Activating Token Index: 5

Text #2

Max Range: 1.4622. Min Range: -1.4622

Max Act: 1.3282. Min Act: -0.0001

Data Index: 831378 (C4 (Web Text))

Max Activating Token Index: 407

Text #3

Max Range: 1.4622. Min Range: -1.4622

Max Act: 1.0451. Min Act: -0.0001

Data Index: 992729 (C4 (Web Text))

Max Activating Token Index: 601

Text #4

Max Range: 1.4622. Min Range: -1.4622

Max Act: 1.1720. Min Act: -0.0001

Data Index: 1358184 (C4 (Web Text))

Max Activating Token Index: 88

Text #5

Max Range: 1.4622. Min Range: -1.4622

Max Act: 1.0763. Min Act: -0.0001

Data Index: 197598 (C4 (Web Text))

Max Activating Token Index: 78

Text #6

Max Range: 1.4622. Min Range: -1.4622

Max Act: 1.1762. Min Act: -0.0001

Data Index: 474972 (C4 (Web Text))

Max Activating Token Index: 343

Text #7

Max Range: 1.4622. Min Range: -1.4622

Max Act: 1.1383. Min Act: -0.0001

Data Index: 1155982 (C4 (Web Text))

Max Activating Token Index: 978

Text #8

Max Range: 1.4622. Min Range: -1.4622

Max Act: 1.1005. Min Act: -0.0001

Data Index: 744814 (C4 (Web Text))

Max Activating Token Index: 6

Text #9

Max Range: 1.4622. Min Range: -1.4622

Max Act: 1.0290. Min Act: -0.0001

Data Index: 1113571 (C4 (Web Text))

Max Activating Token Index: 155

Text #10

Max Range: 1.4622. Min Range: -1.4622

Max Act: 0.9516. Min Act: -0.0001

Data Index: 266476 (C4 (Web Text))

Max Activating Token Index: 234

Text #11

Max Range: 1.4622. Min Range: -1.4622

Max Act: 1.0220. Min Act: -0.0001

Data Index: 16457 (C4 (Web Text))

Max Activating Token Index: 15

Text #12

Max Range: 1.4622. Min Range: -1.4622

Max Act: 1.1552. Min Act: -0.0001

Data Index: 1079697 (C4 (Web Text))

Max Activating Token Index: 796

Text #13

Max Range: 1.4622. Min Range: -1.4622

Max Act: 1.0545. Min Act: -0.0001

Data Index: 767015 (C4 (Web Text))

Max Activating Token Index: 46

Text #14

Max Range: 1.4622. Min Range: -1.4622

Max Act: 1.0672. Min Act: -0.0001

Data Index: 595488 (C4 (Web Text))

Max Activating Token Index: 878

Text #15

Max Range: 1.4622. Min Range: -1.4622

Max Act: 0.9727. Min Act: -0.0001

Data Index: 957802 (C4 (Web Text))

Max Activating Token Index: 530

Text #16

Max Range: 1.4622. Min Range: -1.4622

Max Act: 0.9977. Min Act: -0.0001

Data Index: 756939 (C4 (Web Text))

Max Activating Token Index: 184

Text #17

Max Range: 1.4622. Min Range: -1.4622

Max Act: 1.0289. Min Act: -0.0001

Data Index: 933721 (C4 (Web Text))

Max Activating Token Index: 72

Text #18

Max Range: 1.4622. Min Range: -1.4622

Max Act: 0.9259. Min Act: -0.0001

Data Index: 890149 (C4 (Web Text))

Max Activating Token Index: 991

Text #19

Max Range: 1.4622. Min Range: -1.4622

Max Act: 0.9532. Min Act: -0.0001

Data Index: 877242 (C4 (Web Text))

Max Activating Token Index: 68