Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 2021 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0873. Min Act: -0.0002

Data Index: 1309080 (C4 (Web Text))

Max Activating Token Index: 261

Text #1

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0932. Min Act: -0.0002

Data Index: 550981 (C4 (Web Text))

Max Activating Token Index: 812

Text #2

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0923. Min Act: -0.0002

Data Index: 357765 (C4 (Web Text))

Max Activating Token Index: 405

Text #3

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0936. Min Act: -0.0002

Data Index: 976855 (C4 (Web Text))

Max Activating Token Index: 941

Text #4

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0902. Min Act: -0.0002

Data Index: 665022 (C4 (Web Text))

Max Activating Token Index: 699

Text #5

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0895. Min Act: -0.0002

Data Index: 608372 (C4 (Web Text))

Max Activating Token Index: 217

Text #6

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0866. Min Act: -0.0001

Data Index: 382590 (C4 (Web Text))

Max Activating Token Index: 946

Text #7

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0905. Min Act: -0.0002

Data Index: 596488 (C4 (Web Text))

Max Activating Token Index: 987

Text #8

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0851. Min Act: -0.0001

Data Index: 1355317 (C4 (Web Text))

Max Activating Token Index: 312

Text #9

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0743. Min Act: -0.0002

Data Index: 30110 (C4 (Web Text))

Max Activating Token Index: 681

Text #10

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0819. Min Act: -0.0002

Data Index: 1026602 (C4 (Web Text))

Max Activating Token Index: 309

Text #11

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0807. Min Act: -0.0002

Data Index: 1193874 (C4 (Web Text))

Max Activating Token Index: 812

Text #12

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0850. Min Act: -0.0002

Data Index: 658279 (C4 (Web Text))

Max Activating Token Index: 445

Text #13

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0839. Min Act: -0.0002

Data Index: 1191063 (C4 (Web Text))

Max Activating Token Index: 79

Text #14

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0769. Min Act: -0.0002

Data Index: 575587 (C4 (Web Text))

Max Activating Token Index: 540

Text #15

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0807. Min Act: -0.0002

Data Index: 566761 (C4 (Web Text))

Max Activating Token Index: 151

Text #16

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0817. Min Act: -0.0002

Data Index: 118536 (C4 (Web Text))

Max Activating Token Index: 317

Text #17

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0739. Min Act: -0.0002

Data Index: 440931 (C4 (Web Text))

Max Activating Token Index: 951

Text #18

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0749. Min Act: -0.0002

Data Index: 1038291 (C4 (Web Text))

Max Activating Token Index: 557

Text #19

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0780. Min Act: -0.0002

Data Index: 1057659 (C4 (Web Text))

Max Activating Token Index: 162