Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 235 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0628. Min Act: -0.0004

Data Index: 561284 (C4 (Web Text))

Max Activating Token Index: 195

Text #1

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0578. Min Act: -0.0003

Data Index: 570281 (C4 (Web Text))

Max Activating Token Index: 557

Text #2

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0605. Min Act: -0.0003

Data Index: 534632 (C4 (Web Text))

Max Activating Token Index: 302

Text #3

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0565. Min Act: -0.0003

Data Index: 482693 (C4 (Web Text))

Max Activating Token Index: 829

Text #4

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0558. Min Act: -0.0003

Data Index: 160132 (C4 (Web Text))

Max Activating Token Index: 456

Text #5

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0591. Min Act: -0.0003

Data Index: 181837 (C4 (Web Text))

Max Activating Token Index: 548

Text #6

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0553. Min Act: -0.0003

Data Index: 942474 (C4 (Web Text))

Max Activating Token Index: 776

Text #7

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0508. Min Act: -0.0004

Data Index: 39429 (C4 (Web Text))

Max Activating Token Index: 472

Text #8

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0553. Min Act: -0.0003

Data Index: 154350 (C4 (Web Text))

Max Activating Token Index: 531

Text #9

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0574. Min Act: -0.0004

Data Index: 241006 (C4 (Web Text))

Max Activating Token Index: 934

Text #10

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0505. Min Act: -0.0003

Data Index: 960126 (C4 (Web Text))

Max Activating Token Index: 162

Text #11

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0522. Min Act: -0.0004

Data Index: 820645 (C4 (Web Text))

Max Activating Token Index: 607

Text #12

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0519. Min Act: -0.0002

Data Index: 340078 (C4 (Web Text))

Max Activating Token Index: 154

Text #13

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0492. Min Act: -0.0003

Data Index: 267063 (C4 (Web Text))

Max Activating Token Index: 31

Text #14

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0507. Min Act: -0.0003

Data Index: 1240160 (C4 (Web Text))

Max Activating Token Index: 146

Text #15

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0518. Min Act: -0.0003

Data Index: 987731 (C4 (Web Text))

Max Activating Token Index: 31

Text #16

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0500. Min Act: -0.0003

Data Index: 1346839 (C4 (Web Text))

Max Activating Token Index: 524

Text #17

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0488. Min Act: -0.0002

Data Index: 562672 (C4 (Web Text))

Max Activating Token Index: 982

Text #18

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0480. Min Act: -0.0004

Data Index: 273503 (C4 (Web Text))

Max Activating Token Index: 809

Text #19

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0502. Min Act: -0.0003

Data Index: 1262954 (C4 (Web Text))

Max Activating Token Index: 545