Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3384 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0616. Min Act: -0.0001

Data Index: 473668 (C4 (Web Text))

Max Activating Token Index: 136

Text #1

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0790. Min Act: -0.0001

Data Index: 955883 (C4 (Web Text))

Max Activating Token Index: 860

Text #2

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0792. Min Act: -0.0001

Data Index: 895664 (C4 (Web Text))

Max Activating Token Index: 719

Text #3

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0717. Min Act: -0.0001

Data Index: 131131 (C4 (Web Text))

Max Activating Token Index: 469

Text #4

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0709. Min Act: -0.0001

Data Index: 1059229 (C4 (Web Text))

Max Activating Token Index: 210

Text #5

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0705. Min Act: -0.0001

Data Index: 848529 (C4 (Web Text))

Max Activating Token Index: 871

Text #6

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0732. Min Act: -0.0001

Data Index: 196558 (C4 (Web Text))

Max Activating Token Index: 436

Text #7

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0688. Min Act: -0.0001

Data Index: 588471 (C4 (Web Text))

Max Activating Token Index: 120

Text #8

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0696. Min Act: -0.0001

Data Index: 232734 (C4 (Web Text))

Max Activating Token Index: 87

Text #9

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0628. Min Act: -0.0001

Data Index: 462884 (C4 (Web Text))

Max Activating Token Index: 639

Text #10

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0664. Min Act: -0.0001

Data Index: 168786 (C4 (Web Text))

Max Activating Token Index: 475

Text #11

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0653. Min Act: -0.0001

Data Index: 969235 (C4 (Web Text))

Max Activating Token Index: 767

Text #12

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0619. Min Act: -0.0001

Data Index: 596344 (C4 (Web Text))

Max Activating Token Index: 925

Text #13

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0588. Min Act: -0.0001

Data Index: 1037188 (C4 (Web Text))

Max Activating Token Index: 629

Text #14

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0642. Min Act: -0.0001

Data Index: 411167 (C4 (Web Text))

Max Activating Token Index: 743

Text #15

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0664. Min Act: -0.0001

Data Index: 1295979 (C4 (Web Text))

Max Activating Token Index: 994

Text #16

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0604. Min Act: -0.0001

Data Index: 1267743 (C4 (Web Text))

Max Activating Token Index: 144

Text #17

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0604. Min Act: -0.0001

Data Index: 530710 (C4 (Web Text))

Max Activating Token Index: 514

Text #18

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0624. Min Act: -0.0001

Data Index: 580681 (C4 (Web Text))

Max Activating Token Index: 989

Text #19

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0601. Min Act: -0.0001

Data Index: 560568 (C4 (Web Text))

Max Activating Token Index: 389