Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3938 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.9025. Min Range: -0.9025

Max Act: 0.9025. Min Act: -0.0000

Data Index: 403274 (C4 (Web Text))

Max Activating Token Index: 809

Text #1

Max Range: 0.9025. Min Range: -0.9025

Max Act: 0.8125. Min Act: -0.0000

Data Index: 1246598 (C4 (Web Text))

Max Activating Token Index: 527

Text #2

Max Range: 0.9025. Min Range: -0.9025

Max Act: 0.8121. Min Act: -0.0000

Data Index: 1313451 (C4 (Web Text))

Max Activating Token Index: 122

Text #3

Max Range: 0.9025. Min Range: -0.9025

Max Act: 0.8019. Min Act: -0.0000

Data Index: 1030590 (C4 (Web Text))

Max Activating Token Index: 680

Text #4

Max Range: 0.9025. Min Range: -0.9025

Max Act: 0.8350. Min Act: -0.0000

Data Index: 735209 (C4 (Web Text))

Max Activating Token Index: 111

Text #5

Max Range: 0.9025. Min Range: -0.9025

Max Act: 0.7814. Min Act: -0.0000

Data Index: 738781 (C4 (Web Text))

Max Activating Token Index: 728

Text #6

Max Range: 0.9025. Min Range: -0.9025

Max Act: 0.8594. Min Act: -0.0000

Data Index: 554416 (C4 (Web Text))

Max Activating Token Index: 844

Text #7

Max Range: 0.9025. Min Range: -0.9025

Max Act: 0.7584. Min Act: -0.0000

Data Index: 759142 (C4 (Web Text))

Max Activating Token Index: 302

Text #8

Max Range: 0.9025. Min Range: -0.9025

Max Act: 0.7059. Min Act: -0.0000

Data Index: 494503 (C4 (Web Text))

Max Activating Token Index: 427

Text #9

Max Range: 0.9025. Min Range: -0.9025

Max Act: 0.7498. Min Act: -0.0000

Data Index: 1115528 (C4 (Web Text))

Max Activating Token Index: 735

Text #10

Max Range: 0.9025. Min Range: -0.9025

Max Act: 0.7430. Min Act: -0.0000

Data Index: 1206969 (C4 (Web Text))

Max Activating Token Index: 834

Text #11

Max Range: 0.9025. Min Range: -0.9025

Max Act: 0.7392. Min Act: -0.0000

Data Index: 58238 (C4 (Web Text))

Max Activating Token Index: 751

Text #12

Max Range: 0.9025. Min Range: -0.9025

Max Act: 0.7396. Min Act: -0.0000

Data Index: 22936 (C4 (Web Text))

Max Activating Token Index: 374

Text #13

Max Range: 0.9025. Min Range: -0.9025

Max Act: 0.7333. Min Act: -0.0000

Data Index: 571672 (C4 (Web Text))

Max Activating Token Index: 481

Text #14

Max Range: 0.9025. Min Range: -0.9025

Max Act: 0.7277. Min Act: -0.0000

Data Index: 230079 (C4 (Web Text))

Max Activating Token Index: 97

Text #15

Max Range: 0.9025. Min Range: -0.9025

Max Act: 0.7653. Min Act: -0.0000

Data Index: 1224685 (C4 (Web Text))

Max Activating Token Index: 622

Text #16

Max Range: 0.9025. Min Range: -0.9025

Max Act: 0.6663. Min Act: -0.0000

Data Index: 4012 (C4 (Web Text))

Max Activating Token Index: 400

Text #17

Max Range: 0.9025. Min Range: -0.9025

Max Act: 0.7093. Min Act: -0.0000

Data Index: 307827 (C4 (Web Text))

Max Activating Token Index: 820

Text #18

Max Range: 0.9025. Min Range: -0.9025

Max Act: 0.6979. Min Act: -0.0000

Data Index: 952834 (C4 (Web Text))

Max Activating Token Index: 869

Text #19

Max Range: 0.9025. Min Range: -0.9025

Max Act: 0.6941. Min Act: -0.0000

Data Index: 587088 (C4 (Web Text))

Max Activating Token Index: 769