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

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

Neuron 1001 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0506. Min Range: -1.0506

Max Act: 1.0506. Min Act: 0.0000

Data Index: 614347 (C4 (Web Text))

Max Activating Token Index: 17

Text #1

Max Range: 1.0506. Min Range: -1.0506

Max Act: 0.8995. Min Act: -0.0000

Data Index: 189987 (C4 (Web Text))

Max Activating Token Index: 629

Text #2

Max Range: 1.0506. Min Range: -1.0506

Max Act: 0.8079. Min Act: -0.0000

Data Index: 1145258 (C4 (Web Text))

Max Activating Token Index: 824

Text #3

Max Range: 1.0506. Min Range: -1.0506

Max Act: 0.7754. Min Act: -0.0000

Data Index: 1265525 (C4 (Web Text))

Max Activating Token Index: 456

Text #4

Max Range: 1.0506. Min Range: -1.0506

Max Act: 0.7529. Min Act: -0.0000

Data Index: 320698 (C4 (Web Text))

Max Activating Token Index: 277

Text #5

Max Range: 1.0506. Min Range: -1.0506

Max Act: 0.7244. Min Act: -0.0000

Data Index: 18918 (C4 (Web Text))

Max Activating Token Index: 157

Text #6

Max Range: 1.0506. Min Range: -1.0506

Max Act: 0.7035. Min Act: -0.0000

Data Index: 1124378 (C4 (Web Text))

Max Activating Token Index: 251

Text #7

Max Range: 1.0506. Min Range: -1.0506

Max Act: 0.7034. Min Act: -0.0000

Data Index: 1331170 (C4 (Web Text))

Max Activating Token Index: 941

Text #8

Max Range: 1.0506. Min Range: -1.0506

Max Act: 0.7177. Min Act: -0.0000

Data Index: 1534743 (Python Code)

Max Activating Token Index: 499

Text #9

Max Range: 1.0506. Min Range: -1.0506

Max Act: 0.6897. Min Act: -0.0000

Data Index: 398080 (C4 (Web Text))

Max Activating Token Index: 949

Text #10

Max Range: 1.0506. Min Range: -1.0506

Max Act: 0.7035. Min Act: -0.0000

Data Index: 662823 (C4 (Web Text))

Max Activating Token Index: 59

Text #11

Max Range: 1.0506. Min Range: -1.0506

Max Act: 0.6925. Min Act: -0.0000

Data Index: 217097 (C4 (Web Text))

Max Activating Token Index: 430

Text #12

Max Range: 1.0506. Min Range: -1.0506

Max Act: 0.6636. Min Act: -0.0000

Data Index: 1050697 (C4 (Web Text))

Max Activating Token Index: 110

Text #13

Max Range: 1.0506. Min Range: -1.0506

Max Act: 0.6695. Min Act: -0.0000

Data Index: 102723 (C4 (Web Text))

Max Activating Token Index: 782

Text #14

Max Range: 1.0506. Min Range: -1.0506

Max Act: 0.6831. Min Act: -0.0000

Data Index: 384428 (C4 (Web Text))

Max Activating Token Index: 31

Text #15

Max Range: 1.0506. Min Range: -1.0506

Max Act: 0.6416. Min Act: -0.0000

Data Index: 8445 (C4 (Web Text))

Max Activating Token Index: 494

Text #16

Max Range: 1.0506. Min Range: -1.0506

Max Act: 0.6920. Min Act: -0.0000

Data Index: 234946 (C4 (Web Text))

Max Activating Token Index: 304

Text #17

Max Range: 1.0506. Min Range: -1.0506

Max Act: 0.6670. Min Act: -0.0000

Data Index: 920643 (C4 (Web Text))

Max Activating Token Index: 828

Text #18

Max Range: 1.0506. Min Range: -1.0506

Max Act: 0.6862. Min Act: -0.0000

Data Index: 626989 (C4 (Web Text))

Max Activating Token Index: 977

Text #19

Max Range: 1.0506. Min Range: -1.0506

Max Act: 0.6437. Min Act: -0.0000

Data Index: 973158 (C4 (Web Text))

Max Activating Token Index: 440