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

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

Neuron 4105 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.1035. Min Act: -0.0000

Data Index: 12661 (C4 (Web Text))

Max Activating Token Index: 172

Text #1

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.1044. Min Act: -0.0000

Data Index: 987941 (C4 (Web Text))

Max Activating Token Index: 667

Text #2

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0994. Min Act: -0.0000

Data Index: 422705 (C4 (Web Text))

Max Activating Token Index: 252

Text #3

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0953. Min Act: -0.0000

Data Index: 516983 (C4 (Web Text))

Max Activating Token Index: 32

Text #4

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0904. Min Act: -0.0000

Data Index: 1283253 (C4 (Web Text))

Max Activating Token Index: 274

Text #5

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0876. Min Act: -0.0000

Data Index: 170411 (C4 (Web Text))

Max Activating Token Index: 42

Text #6

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0859. Min Act: -0.0000

Data Index: 402106 (C4 (Web Text))

Max Activating Token Index: 453

Text #7

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0920. Min Act: -0.0000

Data Index: 875283 (C4 (Web Text))

Max Activating Token Index: 208

Text #8

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0832. Min Act: -0.0000

Data Index: 893761 (C4 (Web Text))

Max Activating Token Index: 463

Text #9

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0786. Min Act: -0.0000

Data Index: 674112 (C4 (Web Text))

Max Activating Token Index: 597

Text #10

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0818. Min Act: -0.0000

Data Index: 725363 (C4 (Web Text))

Max Activating Token Index: 332

Text #11

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0803. Min Act: -0.0000

Data Index: 631296 (C4 (Web Text))

Max Activating Token Index: 975

Text #12

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0802. Min Act: -0.0000

Data Index: 128630 (C4 (Web Text))

Max Activating Token Index: 98

Text #13

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0825. Min Act: -0.0000

Data Index: 1030761 (C4 (Web Text))

Max Activating Token Index: 938

Text #14

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0798. Min Act: -0.0000

Data Index: 308096 (C4 (Web Text))

Max Activating Token Index: 349

Text #15

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0795. Min Act: -0.0000

Data Index: 135314 (C4 (Web Text))

Max Activating Token Index: 997

Text #16

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0768. Min Act: -0.0000

Data Index: 639226 (C4 (Web Text))

Max Activating Token Index: 586

Text #17

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0781. Min Act: -0.0000

Data Index: 1316989 (C4 (Web Text))

Max Activating Token Index: 475

Text #18

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0778. Min Act: -0.0000

Data Index: 662180 (C4 (Web Text))

Max Activating Token Index: 285

Text #19

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0805. Min Act: -0.0000

Data Index: 1111950 (C4 (Web Text))

Max Activating Token Index: 1010