Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4613 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.1231. Min Act: -0.0002

Data Index: 789044 (C4 (Web Text))

Max Activating Token Index: 584

Text #1

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.1052. Min Act: -0.0002

Data Index: 291914 (C4 (Web Text))

Max Activating Token Index: 925

Text #2

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.0847. Min Act: -0.0002

Data Index: 1019310 (C4 (Web Text))

Max Activating Token Index: 212

Text #3

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.0804. Min Act: -0.0002

Data Index: 216615 (C4 (Web Text))

Max Activating Token Index: 90

Text #4

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.0748. Min Act: -0.0002

Data Index: 828546 (C4 (Web Text))

Max Activating Token Index: 627

Text #5

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.0778. Min Act: -0.0002

Data Index: 213607 (C4 (Web Text))

Max Activating Token Index: 601

Text #6

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.0749. Min Act: -0.0002

Data Index: 697523 (C4 (Web Text))

Max Activating Token Index: 992

Text #7

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.0746. Min Act: -0.0002

Data Index: 703377 (C4 (Web Text))

Max Activating Token Index: 911

Text #8

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.0731. Min Act: -0.0002

Data Index: 13701 (C4 (Web Text))

Max Activating Token Index: 521

Text #9

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.0703. Min Act: -0.0002

Data Index: 1354688 (C4 (Web Text))

Max Activating Token Index: 627

Text #10

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.0703. Min Act: -0.0002

Data Index: 215901 (C4 (Web Text))

Max Activating Token Index: 391

Text #11

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.0702. Min Act: -0.0002

Data Index: 439190 (C4 (Web Text))

Max Activating Token Index: 881

Text #12

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.0699. Min Act: -0.0002

Data Index: 41285 (C4 (Web Text))

Max Activating Token Index: 52

Text #13

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.0741. Min Act: -0.0002

Data Index: 1135823 (C4 (Web Text))

Max Activating Token Index: 941

Text #14

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.0736. Min Act: -0.0002

Data Index: 609638 (C4 (Web Text))

Max Activating Token Index: 726

Text #15

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.0706. Min Act: -0.0002

Data Index: 850079 (C4 (Web Text))

Max Activating Token Index: 223

Text #16

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.0698. Min Act: -0.0002

Data Index: 723486 (C4 (Web Text))

Max Activating Token Index: 422

Text #17

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.0697. Min Act: -0.0002

Data Index: 860138 (C4 (Web Text))

Max Activating Token Index: 33

Text #18

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.0722. Min Act: -0.0002

Data Index: 1079840 (C4 (Web Text))

Max Activating Token Index: 378

Text #19

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.0688. Min Act: -0.0002

Data Index: 1311824 (C4 (Web Text))

Max Activating Token Index: 654