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

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

Neuron 4701 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0934. Min Act: -0.0002

Data Index: 395909 (C4 (Web Text))

Max Activating Token Index: 603

Text #1

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0848. Min Act: -0.0003

Data Index: 1042527 (C4 (Web Text))

Max Activating Token Index: 539

Text #2

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0875. Min Act: -0.0002

Data Index: 1096406 (C4 (Web Text))

Max Activating Token Index: 617

Text #3

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0880. Min Act: -0.0003

Data Index: 677419 (C4 (Web Text))

Max Activating Token Index: 573

Text #4

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0843. Min Act: -0.0002

Data Index: 760675 (C4 (Web Text))

Max Activating Token Index: 675

Text #5

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0853. Min Act: -0.0003

Data Index: 1330263 (C4 (Web Text))

Max Activating Token Index: 656

Text #6

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0926. Min Act: -0.0002

Data Index: 585222 (C4 (Web Text))

Max Activating Token Index: 777

Text #7

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0861. Min Act: -0.0002

Data Index: 1127344 (C4 (Web Text))

Max Activating Token Index: 546

Text #8

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0798. Min Act: -0.0002

Data Index: 34173 (C4 (Web Text))

Max Activating Token Index: 632

Text #9

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0812. Min Act: -0.0002

Data Index: 1121235 (C4 (Web Text))

Max Activating Token Index: 617

Text #10

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0883. Min Act: -0.0002

Data Index: 76649 (C4 (Web Text))

Max Activating Token Index: 81

Text #11

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0837. Min Act: -0.0003

Data Index: 1083114 (C4 (Web Text))

Max Activating Token Index: 578

Text #12

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0818. Min Act: -0.0003

Data Index: 41466 (C4 (Web Text))

Max Activating Token Index: 686

Text #13

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0819. Min Act: -0.0002

Data Index: 131465 (C4 (Web Text))

Max Activating Token Index: 301

Text #14

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0842. Min Act: -0.0003

Data Index: 262984 (C4 (Web Text))

Max Activating Token Index: 858

Text #15

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0814. Min Act: -0.0003

Data Index: 830239 (C4 (Web Text))

Max Activating Token Index: 677

Text #16

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0841. Min Act: -0.0003

Data Index: 902992 (C4 (Web Text))

Max Activating Token Index: 886

Text #17

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0844. Min Act: -0.0002

Data Index: 1147489 (C4 (Web Text))

Max Activating Token Index: 673

Text #18

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0858. Min Act: -0.0002

Data Index: 676804 (C4 (Web Text))

Max Activating Token Index: 886

Text #19

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0791. Min Act: -0.0002

Data Index: 703675 (C4 (Web Text))

Max Activating Token Index: 713