Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1754 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0850. Min Act: -0.0003

Data Index: 844473 (C4 (Web Text))

Max Activating Token Index: 71

Text #1

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0819. Min Act: -0.0003

Data Index: 806951 (C4 (Web Text))

Max Activating Token Index: 826

Text #2

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0803. Min Act: -0.0003

Data Index: 621063 (C4 (Web Text))

Max Activating Token Index: 678

Text #3

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0805. Min Act: -0.0003

Data Index: 192975 (C4 (Web Text))

Max Activating Token Index: 492

Text #4

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0802. Min Act: -0.0003

Data Index: 913438 (C4 (Web Text))

Max Activating Token Index: 108

Text #5

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0798. Min Act: -0.0003

Data Index: 1235921 (C4 (Web Text))

Max Activating Token Index: 394

Text #6

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0786. Min Act: -0.0003

Data Index: 1072713 (C4 (Web Text))

Max Activating Token Index: 957

Text #7

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0763. Min Act: -0.0003

Data Index: 263582 (C4 (Web Text))

Max Activating Token Index: 237

Text #8

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0755. Min Act: -0.0002

Data Index: 408075 (C4 (Web Text))

Max Activating Token Index: 992

Text #9

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0741. Min Act: -0.0002

Data Index: 1298989 (C4 (Web Text))

Max Activating Token Index: 818

Text #10

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0730. Min Act: -0.0003

Data Index: 113052 (C4 (Web Text))

Max Activating Token Index: 237

Text #11

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0740. Min Act: -0.0002

Data Index: 1313106 (C4 (Web Text))

Max Activating Token Index: 481

Text #12

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0723. Min Act: -0.0002

Data Index: 1317365 (C4 (Web Text))

Max Activating Token Index: 273

Text #13

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0710. Min Act: -0.0003

Data Index: 1133959 (C4 (Web Text))

Max Activating Token Index: 431

Text #14

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0720. Min Act: -0.0003

Data Index: 894873 (C4 (Web Text))

Max Activating Token Index: 631

Text #15

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0717. Min Act: -0.0003

Data Index: 917782 (C4 (Web Text))

Max Activating Token Index: 990

Text #16

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0714. Min Act: -0.0003

Data Index: 872976 (C4 (Web Text))

Max Activating Token Index: 708

Text #17

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0717. Min Act: -0.0003

Data Index: 174728 (C4 (Web Text))

Max Activating Token Index: 456

Text #18

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0705. Min Act: -0.0002

Data Index: 421386 (C4 (Web Text))

Max Activating Token Index: 503

Text #19

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0714. Min Act: -0.0003

Data Index: 960936 (C4 (Web Text))

Max Activating Token Index: 832