Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 624 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0765. Min Act: -0.0001

Data Index: 390746 (C4 (Web Text))

Max Activating Token Index: 83

Text #1

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0748. Min Act: -0.0001

Data Index: 461793 (C4 (Web Text))

Max Activating Token Index: 156

Text #2

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0755. Min Act: -0.0001

Data Index: 1121963 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0729. Min Act: -0.0001

Data Index: 802741 (C4 (Web Text))

Max Activating Token Index: 70

Text #4

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0729. Min Act: -0.0001

Data Index: 1133883 (C4 (Web Text))

Max Activating Token Index: 779

Text #5

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0684. Min Act: -0.0001

Data Index: 449615 (C4 (Web Text))

Max Activating Token Index: 123

Text #6

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0691. Min Act: -0.0001

Data Index: 703497 (C4 (Web Text))

Max Activating Token Index: 659

Text #7

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0663. Min Act: -0.0001

Data Index: 1251436 (C4 (Web Text))

Max Activating Token Index: 681

Text #8

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0647. Min Act: -0.0001

Data Index: 684353 (C4 (Web Text))

Max Activating Token Index: 197

Text #9

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0628. Min Act: -0.0001

Data Index: 372173 (C4 (Web Text))

Max Activating Token Index: 270

Text #10

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0623. Min Act: -0.0001

Data Index: 387643 (C4 (Web Text))

Max Activating Token Index: 246

Text #11

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0656. Min Act: -0.0001

Data Index: 359474 (C4 (Web Text))

Max Activating Token Index: 483

Text #12

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0659. Min Act: -0.0001

Data Index: 53671 (C4 (Web Text))

Max Activating Token Index: 677

Text #13

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0619. Min Act: -0.0001

Data Index: 1214965 (C4 (Web Text))

Max Activating Token Index: 768

Text #14

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0633. Min Act: -0.0001

Data Index: 500672 (C4 (Web Text))

Max Activating Token Index: 407

Text #15

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0612. Min Act: -0.0001

Data Index: 777399 (C4 (Web Text))

Max Activating Token Index: 589

Text #16

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0614. Min Act: -0.0001

Data Index: 235371 (C4 (Web Text))

Max Activating Token Index: 117

Text #17

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0587. Min Act: -0.0001

Data Index: 1137473 (C4 (Web Text))

Max Activating Token Index: 273

Text #18

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0583. Min Act: -0.0001

Data Index: 596190 (C4 (Web Text))

Max Activating Token Index: 545

Text #19

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0655. Min Act: -0.0001

Data Index: 1019958 (C4 (Web Text))

Max Activating Token Index: 77