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

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

Neuron 384 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: 0.0698. Min Range: -0.0698

Max Act: 0.0698. Min Act: -0.0002

Data Index: 968077 (C4 (Web Text))

Max Activating Token Index: 617

Text #1

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0695. Min Act: -0.0002

Data Index: 141800 (C4 (Web Text))

Max Activating Token Index: 815

Text #2

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0664. Min Act: -0.0002

Data Index: 959333 (C4 (Web Text))

Max Activating Token Index: 770

Text #3

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0673. Min Act: -0.0002

Data Index: 1103262 (C4 (Web Text))

Max Activating Token Index: 819

Text #4

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0634. Min Act: -0.0002

Data Index: 488616 (C4 (Web Text))

Max Activating Token Index: 402

Text #5

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0623. Min Act: -0.0002

Data Index: 876371 (C4 (Web Text))

Max Activating Token Index: 10

Text #6

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0617. Min Act: -0.0002

Data Index: 1084077 (C4 (Web Text))

Max Activating Token Index: 214

Text #7

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0594. Min Act: -0.0002

Data Index: 492089 (C4 (Web Text))

Max Activating Token Index: 760

Text #8

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0577. Min Act: -0.0002

Data Index: 66310 (C4 (Web Text))

Max Activating Token Index: 667

Text #9

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0601. Min Act: -0.0002

Data Index: 1308107 (C4 (Web Text))

Max Activating Token Index: 21

Text #10

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0602. Min Act: -0.0002

Data Index: 627823 (C4 (Web Text))

Max Activating Token Index: 810

Text #11

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0578. Min Act: -0.0002

Data Index: 1087907 (C4 (Web Text))

Max Activating Token Index: 296

Text #12

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0576. Min Act: -0.0002

Data Index: 350525 (C4 (Web Text))

Max Activating Token Index: 231

Text #13

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0605. Min Act: -0.0002

Data Index: 1299148 (C4 (Web Text))

Max Activating Token Index: 372

Text #14

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0573. Min Act: -0.0002

Data Index: 634994 (C4 (Web Text))

Max Activating Token Index: 842

Text #15

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0596. Min Act: -0.0002

Data Index: 317500 (C4 (Web Text))

Max Activating Token Index: 987

Text #16

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0578. Min Act: -0.0002

Data Index: 670552 (C4 (Web Text))

Max Activating Token Index: 296

Text #17

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0572. Min Act: -0.0002

Data Index: 823415 (C4 (Web Text))

Max Activating Token Index: 19

Text #18

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0558. Min Act: -0.0002

Data Index: 434301 (C4 (Web Text))

Max Activating Token Index: 26

Text #19

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0561. Min Act: -0.0002

Data Index: 964275 (C4 (Web Text))

Max Activating Token Index: 129