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

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

Neuron 1473 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0704. Min Act: -0.0006

Data Index: 1065726 (C4 (Web Text))

Max Activating Token Index: 777

Text #1

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0660. Min Act: -0.0006

Data Index: 140119 (C4 (Web Text))

Max Activating Token Index: 189

Text #2

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0633. Min Act: -0.0006

Data Index: 535103 (C4 (Web Text))

Max Activating Token Index: 634

Text #3

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0627. Min Act: -0.0006

Data Index: 1098464 (C4 (Web Text))

Max Activating Token Index: 106

Text #4

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0610. Min Act: -0.0006

Data Index: 1224564 (C4 (Web Text))

Max Activating Token Index: 128

Text #5

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0588. Min Act: -0.0006

Data Index: 599074 (C4 (Web Text))

Max Activating Token Index: 541

Text #6

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0582. Min Act: -0.0006

Data Index: 1317871 (C4 (Web Text))

Max Activating Token Index: 400

Text #7

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0597. Min Act: -0.0006

Data Index: 996916 (C4 (Web Text))

Max Activating Token Index: 502

Text #8

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0559. Min Act: -0.0006

Data Index: 217378 (C4 (Web Text))

Max Activating Token Index: 228

Text #9

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0573. Min Act: -0.0006

Data Index: 707651 (C4 (Web Text))

Max Activating Token Index: 538

Text #10

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0559. Min Act: -0.0006

Data Index: 733285 (C4 (Web Text))

Max Activating Token Index: 44

Text #11

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0547. Min Act: -0.0006

Data Index: 446806 (C4 (Web Text))

Max Activating Token Index: 165

Text #12

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0511. Min Act: -0.0006

Data Index: 332402 (C4 (Web Text))

Max Activating Token Index: 613

Text #13

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0561. Min Act: -0.0006

Data Index: 1143469 (C4 (Web Text))

Max Activating Token Index: 568

Text #14

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0536. Min Act: -0.0006

Data Index: 47439 (C4 (Web Text))

Max Activating Token Index: 833

Text #15

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0535. Min Act: -0.0006

Data Index: 626494 (C4 (Web Text))

Max Activating Token Index: 111

Text #16

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0524. Min Act: -0.0006

Data Index: 635116 (C4 (Web Text))

Max Activating Token Index: 688

Text #17

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0531. Min Act: -0.0006

Data Index: 764871 (C4 (Web Text))

Max Activating Token Index: 208

Text #18

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0543. Min Act: -0.0006

Data Index: 826123 (C4 (Web Text))

Max Activating Token Index: 650

Text #19

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0519. Min Act: -0.0006

Data Index: 174079 (C4 (Web Text))

Max Activating Token Index: 719