Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 552 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0677. Min Act: -0.0000

Data Index: 1233466 (C4 (Web Text))

Max Activating Token Index: 645

Text #1

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0702. Min Act: -0.0000

Data Index: 94050 (C4 (Web Text))

Max Activating Token Index: 563

Text #2

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0641. Min Act: -0.0000

Data Index: 747546 (C4 (Web Text))

Max Activating Token Index: 724

Text #3

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0614. Min Act: -0.0000

Data Index: 876181 (C4 (Web Text))

Max Activating Token Index: 742

Text #4

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0599. Min Act: -0.0000

Data Index: 134372 (C4 (Web Text))

Max Activating Token Index: 690

Text #5

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0541. Min Act: -0.0000

Data Index: 943875 (C4 (Web Text))

Max Activating Token Index: 969

Text #6

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0597. Min Act: -0.0000

Data Index: 68265 (C4 (Web Text))

Max Activating Token Index: 457

Text #7

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0576. Min Act: -0.0000

Data Index: 909303 (C4 (Web Text))

Max Activating Token Index: 844

Text #8

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0608. Min Act: -0.0000

Data Index: 763002 (C4 (Web Text))

Max Activating Token Index: 151

Text #9

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0556. Min Act: -0.0000

Data Index: 241698 (C4 (Web Text))

Max Activating Token Index: 915

Text #10

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0541. Min Act: -0.0000

Data Index: 112591 (C4 (Web Text))

Max Activating Token Index: 852

Text #11

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0554. Min Act: -0.0000

Data Index: 1174512 (C4 (Web Text))

Max Activating Token Index: 672

Text #12

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0556. Min Act: -0.0000

Data Index: 525744 (C4 (Web Text))

Max Activating Token Index: 565

Text #13

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0551. Min Act: -0.0000

Data Index: 192661 (C4 (Web Text))

Max Activating Token Index: 877

Text #14

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0585. Min Act: -0.0000

Data Index: 1452924 (Python Code)

Max Activating Token Index: 649

Text #15

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0550. Min Act: -0.0000

Data Index: 1036910 (C4 (Web Text))

Max Activating Token Index: 1022

Text #16

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0544. Min Act: -0.0000

Data Index: 793084 (C4 (Web Text))

Max Activating Token Index: 906

Text #17

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0526. Min Act: -0.0000

Data Index: 486099 (C4 (Web Text))

Max Activating Token Index: 970

Text #18

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0544. Min Act: -0.0000

Data Index: 1024827 (C4 (Web Text))

Max Activating Token Index: 747

Text #19

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0509. Min Act: -0.0000

Data Index: 759223 (C4 (Web Text))

Max Activating Token Index: 96