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

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

Neuron 1641 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: 0.0769. Min Range: -0.0769

Max Act: 0.0722. Min Act: -0.0002

Data Index: 735914 (C4 (Web Text))

Max Activating Token Index: 764

Text #1

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0769. Min Act: -0.0002

Data Index: 947224 (C4 (Web Text))

Max Activating Token Index: 778

Text #2

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0655. Min Act: -0.0001

Data Index: 1065499 (C4 (Web Text))

Max Activating Token Index: 961

Text #3

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0641. Min Act: -0.0002

Data Index: 405987 (C4 (Web Text))

Max Activating Token Index: 152

Text #4

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0644. Min Act: -0.0002

Data Index: 797590 (C4 (Web Text))

Max Activating Token Index: 983

Text #5

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0650. Min Act: -0.0002

Data Index: 1214642 (C4 (Web Text))

Max Activating Token Index: 513

Text #6

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0637. Min Act: -0.0002

Data Index: 291040 (C4 (Web Text))

Max Activating Token Index: 122

Text #7

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0630. Min Act: -0.0001

Data Index: 1071436 (C4 (Web Text))

Max Activating Token Index: 754

Text #8

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0625. Min Act: -0.0002

Data Index: 574136 (C4 (Web Text))

Max Activating Token Index: 588

Text #9

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0607. Min Act: -0.0002

Data Index: 160658 (C4 (Web Text))

Max Activating Token Index: 314

Text #10

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0598. Min Act: -0.0002

Data Index: 277157 (C4 (Web Text))

Max Activating Token Index: 789

Text #11

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0619. Min Act: -0.0002

Data Index: 1206630 (C4 (Web Text))

Max Activating Token Index: 760

Text #12

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0589. Min Act: -0.0001

Data Index: 1196586 (C4 (Web Text))

Max Activating Token Index: 610

Text #13

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0599. Min Act: -0.0002

Data Index: 1290275 (C4 (Web Text))

Max Activating Token Index: 54

Text #14

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0580. Min Act: -0.0001

Data Index: 198097 (C4 (Web Text))

Max Activating Token Index: 167

Text #15

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0580. Min Act: -0.0002

Data Index: 475325 (C4 (Web Text))

Max Activating Token Index: 443

Text #16

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0594. Min Act: -0.0002

Data Index: 787366 (C4 (Web Text))

Max Activating Token Index: 229

Text #17

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0605. Min Act: -0.0001

Data Index: 404258 (C4 (Web Text))

Max Activating Token Index: 83

Text #18

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0590. Min Act: -0.0002

Data Index: 1375782 (Python Code)

Max Activating Token Index: 707

Text #19

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0563. Min Act: -0.0002

Data Index: 291532 (C4 (Web Text))

Max Activating Token Index: 124