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

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

Neuron 439 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0801. Min Range: -1.0801

Max Act: 1.0801. Min Act: -0.0001

Data Index: 853694 (C4 (Web Text))

Max Activating Token Index: 73

Text #1

Max Range: 1.0801. Min Range: -1.0801

Max Act: 0.9636. Min Act: -0.0001

Data Index: 1164958 (C4 (Web Text))

Max Activating Token Index: 130

Text #2

Max Range: 1.0801. Min Range: -1.0801

Max Act: 0.9017. Min Act: -0.0001

Data Index: 1146277 (C4 (Web Text))

Max Activating Token Index: 337

Text #3

Max Range: 1.0801. Min Range: -1.0801

Max Act: 0.7714. Min Act: -0.0001

Data Index: 190563 (C4 (Web Text))

Max Activating Token Index: 816

Text #4

Max Range: 1.0801. Min Range: -1.0801

Max Act: 0.8516. Min Act: -0.0001

Data Index: 315541 (C4 (Web Text))

Max Activating Token Index: 921

Text #5

Max Range: 1.0801. Min Range: -1.0801

Max Act: 0.7392. Min Act: -0.0001

Data Index: 1295294 (C4 (Web Text))

Max Activating Token Index: 502

Text #6

Max Range: 1.0801. Min Range: -1.0801

Max Act: 0.7603. Min Act: -0.0001

Data Index: 1165893 (C4 (Web Text))

Max Activating Token Index: 1001

Text #7

Max Range: 1.0801. Min Range: -1.0801

Max Act: 0.7039. Min Act: -0.0001

Data Index: 360045 (C4 (Web Text))

Max Activating Token Index: 481

Text #8

Max Range: 1.0801. Min Range: -1.0801

Max Act: 0.8003. Min Act: -0.0001

Data Index: 176614 (C4 (Web Text))

Max Activating Token Index: 368

Text #9

Max Range: 1.0801. Min Range: -1.0801

Max Act: 0.7393. Min Act: -0.0001

Data Index: 49413 (C4 (Web Text))

Max Activating Token Index: 558

Text #10

Max Range: 1.0801. Min Range: -1.0801

Max Act: 0.6987. Min Act: -0.0001

Data Index: 128988 (C4 (Web Text))

Max Activating Token Index: 88

Text #11

Max Range: 1.0801. Min Range: -1.0801

Max Act: 0.6964. Min Act: -0.0001

Data Index: 742579 (C4 (Web Text))

Max Activating Token Index: 408

Text #12

Max Range: 1.0801. Min Range: -1.0801

Max Act: 0.6978. Min Act: -0.0001

Data Index: 908902 (C4 (Web Text))

Max Activating Token Index: 488

Text #13

Max Range: 1.0801. Min Range: -1.0801

Max Act: 0.6647. Min Act: -0.0001

Data Index: 952635 (C4 (Web Text))

Max Activating Token Index: 34

Text #14

Max Range: 1.0801. Min Range: -1.0801

Max Act: 0.7118. Min Act: -0.0001

Data Index: 228888 (C4 (Web Text))

Max Activating Token Index: 779

Text #15

Max Range: 1.0801. Min Range: -1.0801

Max Act: 0.6999. Min Act: -0.0001

Data Index: 411666 (C4 (Web Text))

Max Activating Token Index: 808

Text #16

Max Range: 1.0801. Min Range: -1.0801

Max Act: 0.6540. Min Act: -0.0001

Data Index: 290360 (C4 (Web Text))

Max Activating Token Index: 408

Text #17

Max Range: 1.0801. Min Range: -1.0801

Max Act: 0.6325. Min Act: -0.0001

Data Index: 839469 (C4 (Web Text))

Max Activating Token Index: 172

Text #18

Max Range: 1.0801. Min Range: -1.0801

Max Act: 0.6056. Min Act: -0.0001

Data Index: 758054 (C4 (Web Text))

Max Activating Token Index: 843

Text #19

Max Range: 1.0801. Min Range: -1.0801

Max Act: 0.6423. Min Act: -0.0001

Data Index: 995970 (C4 (Web Text))

Max Activating Token Index: 36