Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 343 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0842. Min Range: -1.0842

Max Act: 1.0842. Min Act: -0.0001

Data Index: 965195 (C4 (Web Text))

Max Activating Token Index: 678

Text #1

Max Range: 1.0842. Min Range: -1.0842

Max Act: 0.9748. Min Act: -0.0001

Data Index: 1220624 (C4 (Web Text))

Max Activating Token Index: 638

Text #2

Max Range: 1.0842. Min Range: -1.0842

Max Act: 0.8392. Min Act: -0.0001

Data Index: 344500 (C4 (Web Text))

Max Activating Token Index: 150

Text #3

Max Range: 1.0842. Min Range: -1.0842

Max Act: 0.9158. Min Act: -0.0001

Data Index: 556778 (C4 (Web Text))

Max Activating Token Index: 1007

Text #4

Max Range: 1.0842. Min Range: -1.0842

Max Act: 0.8839. Min Act: -0.0001

Data Index: 255239 (C4 (Web Text))

Max Activating Token Index: 1002

Text #5

Max Range: 1.0842. Min Range: -1.0842

Max Act: 0.9886. Min Act: -0.0001

Data Index: 345385 (C4 (Web Text))

Max Activating Token Index: 835

Text #6

Max Range: 1.0842. Min Range: -1.0842

Max Act: 0.8691. Min Act: -0.0001

Data Index: 257752 (C4 (Web Text))

Max Activating Token Index: 803

Text #7

Max Range: 1.0842. Min Range: -1.0842

Max Act: 0.9167. Min Act: -0.0001

Data Index: 650272 (C4 (Web Text))

Max Activating Token Index: 460

Text #8

Max Range: 1.0842. Min Range: -1.0842

Max Act: 0.9319. Min Act: -0.0001

Data Index: 416766 (C4 (Web Text))

Max Activating Token Index: 758

Text #9

Max Range: 1.0842. Min Range: -1.0842

Max Act: 0.8461. Min Act: -0.0001

Data Index: 320646 (C4 (Web Text))

Max Activating Token Index: 557

Text #10

Max Range: 1.0842. Min Range: -1.0842

Max Act: 0.8294. Min Act: -0.0001

Data Index: 103458 (C4 (Web Text))

Max Activating Token Index: 185

Text #11

Max Range: 1.0842. Min Range: -1.0842

Max Act: 0.8754. Min Act: -0.0001

Data Index: 644232 (C4 (Web Text))

Max Activating Token Index: 49

Text #12

Max Range: 1.0842. Min Range: -1.0842

Max Act: 0.8421. Min Act: -0.0001

Data Index: 178909 (C4 (Web Text))

Max Activating Token Index: 426

Text #13

Max Range: 1.0842. Min Range: -1.0842

Max Act: 0.8121. Min Act: -0.0001

Data Index: 733114 (C4 (Web Text))

Max Activating Token Index: 716

Text #14

Max Range: 1.0842. Min Range: -1.0842

Max Act: 0.8093. Min Act: -0.0001

Data Index: 1166759 (C4 (Web Text))

Max Activating Token Index: 540

Text #15

Max Range: 1.0842. Min Range: -1.0842

Max Act: 0.8055. Min Act: -0.0001

Data Index: 4879 (C4 (Web Text))

Max Activating Token Index: 495

Text #16

Max Range: 1.0842. Min Range: -1.0842

Max Act: 0.8267. Min Act: -0.0001

Data Index: 1025014 (C4 (Web Text))

Max Activating Token Index: 63

Text #17

Max Range: 1.0842. Min Range: -1.0842

Max Act: 0.8056. Min Act: -0.0001

Data Index: 711619 (C4 (Web Text))

Max Activating Token Index: 679

Text #18

Max Range: 1.0842. Min Range: -1.0842

Max Act: 0.8326. Min Act: -0.0001

Data Index: 745718 (C4 (Web Text))

Max Activating Token Index: 790

Text #19

Max Range: 1.0842. Min Range: -1.0842

Max Act: 0.8219. Min Act: -0.0001

Data Index: 1184282 (C4 (Web Text))

Max Activating Token Index: 392