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

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

Neuron 571 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3689. Min Range: -1.3689

Max Act: 1.3689. Min Act: -0.0000

Data Index: 481712 (C4 (Web Text))

Max Activating Token Index: 12

Text #1

Max Range: 1.3689. Min Range: -1.3689

Max Act: 1.0556. Min Act: -0.0000

Data Index: 1269799 (C4 (Web Text))

Max Activating Token Index: 565

Text #2

Max Range: 1.3689. Min Range: -1.3689

Max Act: 0.9063. Min Act: -0.0000

Data Index: 307599 (C4 (Web Text))

Max Activating Token Index: 1004

Text #3

Max Range: 1.3689. Min Range: -1.3689

Max Act: 0.8862. Min Act: -0.0000

Data Index: 521908 (C4 (Web Text))

Max Activating Token Index: 523

Text #4

Max Range: 1.3689. Min Range: -1.3689

Max Act: 0.8869. Min Act: -0.0000

Data Index: 1097008 (C4 (Web Text))

Max Activating Token Index: 363

Text #5

Max Range: 1.3689. Min Range: -1.3689

Max Act: 0.8481. Min Act: -0.0000

Data Index: 56942 (C4 (Web Text))

Max Activating Token Index: 548

Text #6

Max Range: 1.3689. Min Range: -1.3689

Max Act: 0.8980. Min Act: -0.0000

Data Index: 1167935 (C4 (Web Text))

Max Activating Token Index: 49

Text #7

Max Range: 1.3689. Min Range: -1.3689

Max Act: 0.8998. Min Act: -0.0000

Data Index: 936184 (C4 (Web Text))

Max Activating Token Index: 38

Text #8

Max Range: 1.3689. Min Range: -1.3689

Max Act: 0.8675. Min Act: -0.0000

Data Index: 870645 (C4 (Web Text))

Max Activating Token Index: 175

Text #9

Max Range: 1.3689. Min Range: -1.3689

Max Act: 0.8941. Min Act: -0.0000

Data Index: 917556 (C4 (Web Text))

Max Activating Token Index: 118

Text #10

Max Range: 1.3689. Min Range: -1.3689

Max Act: 0.8646. Min Act: -0.0000

Data Index: 662287 (C4 (Web Text))

Max Activating Token Index: 242

Text #11

Max Range: 1.3689. Min Range: -1.3689

Max Act: 0.8828. Min Act: -0.0000

Data Index: 913433 (C4 (Web Text))

Max Activating Token Index: 471

Text #12

Max Range: 1.3689. Min Range: -1.3689

Max Act: 0.8545. Min Act: -0.0000

Data Index: 211388 (C4 (Web Text))

Max Activating Token Index: 438

Text #13

Max Range: 1.3689. Min Range: -1.3689

Max Act: 0.8361. Min Act: -0.0000

Data Index: 826360 (C4 (Web Text))

Max Activating Token Index: 857

Text #14

Max Range: 1.3689. Min Range: -1.3689

Max Act: 0.7928. Min Act: -0.0000

Data Index: 1154718 (C4 (Web Text))

Max Activating Token Index: 467

Text #15

Max Range: 1.3689. Min Range: -1.3689

Max Act: 0.8410. Min Act: -0.0000

Data Index: 777325 (C4 (Web Text))

Max Activating Token Index: 787

Text #16

Max Range: 1.3689. Min Range: -1.3689

Max Act: 0.7787. Min Act: -0.0000

Data Index: 1231327 (C4 (Web Text))

Max Activating Token Index: 31

Text #17

Max Range: 1.3689. Min Range: -1.3689

Max Act: 0.8110. Min Act: -0.0000

Data Index: 645721 (C4 (Web Text))

Max Activating Token Index: 89

Text #18

Max Range: 1.3689. Min Range: -1.3689

Max Act: 0.8429. Min Act: -0.0000

Data Index: 972495 (C4 (Web Text))

Max Activating Token Index: 255

Text #19

Max Range: 1.3689. Min Range: -1.3689

Max Act: 0.7492. Min Act: -0.0000

Data Index: 266230 (C4 (Web Text))

Max Activating Token Index: 558