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

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

Neuron 480 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: 0.0983. Min Range: -0.0983

Max Act: 0.0983. Min Act: -0.0003

Data Index: 880619 (C4 (Web Text))

Max Activating Token Index: 218

Text #1

Max Range: 0.0983. Min Range: -0.0983

Max Act: 0.0866. Min Act: -0.0004

Data Index: 1332718 (C4 (Web Text))

Max Activating Token Index: 155

Text #2

Max Range: 0.0983. Min Range: -0.0983

Max Act: 0.0816. Min Act: -0.0003

Data Index: 551380 (C4 (Web Text))

Max Activating Token Index: 520

Text #3

Max Range: 0.0983. Min Range: -0.0983

Max Act: 0.0772. Min Act: -0.0003

Data Index: 521578 (C4 (Web Text))

Max Activating Token Index: 546

Text #4

Max Range: 0.0983. Min Range: -0.0983

Max Act: 0.0804. Min Act: -0.0003

Data Index: 14483 (C4 (Web Text))

Max Activating Token Index: 864

Text #5

Max Range: 0.0983. Min Range: -0.0983

Max Act: 0.0820. Min Act: -0.0004

Data Index: 791041 (C4 (Web Text))

Max Activating Token Index: 122

Text #6

Max Range: 0.0983. Min Range: -0.0983

Max Act: 0.0744. Min Act: -0.0004

Data Index: 912098 (C4 (Web Text))

Max Activating Token Index: 783

Text #7

Max Range: 0.0983. Min Range: -0.0983

Max Act: 0.0723. Min Act: -0.0003

Data Index: 92125 (C4 (Web Text))

Max Activating Token Index: 559

Text #8

Max Range: 0.0983. Min Range: -0.0983

Max Act: 0.0747. Min Act: -0.0003

Data Index: 581073 (C4 (Web Text))

Max Activating Token Index: 463

Text #9

Max Range: 0.0983. Min Range: -0.0983

Max Act: 0.0685. Min Act: -0.0003

Data Index: 677564 (C4 (Web Text))

Max Activating Token Index: 492

Text #10

Max Range: 0.0983. Min Range: -0.0983

Max Act: 0.0678. Min Act: -0.0003

Data Index: 979053 (C4 (Web Text))

Max Activating Token Index: 640

Text #11

Max Range: 0.0983. Min Range: -0.0983

Max Act: 0.0695. Min Act: -0.0003

Data Index: 1301129 (C4 (Web Text))

Max Activating Token Index: 24

Text #12

Max Range: 0.0983. Min Range: -0.0983

Max Act: 0.0670. Min Act: -0.0004

Data Index: 685290 (C4 (Web Text))

Max Activating Token Index: 186

Text #13

Max Range: 0.0983. Min Range: -0.0983

Max Act: 0.0689. Min Act: -0.0003

Data Index: 579640 (C4 (Web Text))

Max Activating Token Index: 88

Text #14

Max Range: 0.0983. Min Range: -0.0983

Max Act: 0.0680. Min Act: -0.0002

Data Index: 631965 (C4 (Web Text))

Max Activating Token Index: 467

Text #15

Max Range: 0.0983. Min Range: -0.0983

Max Act: 0.0665. Min Act: -0.0003

Data Index: 1121115 (C4 (Web Text))

Max Activating Token Index: 511

Text #16

Max Range: 0.0983. Min Range: -0.0983

Max Act: 0.0701. Min Act: -0.0003

Data Index: 1328103 (C4 (Web Text))

Max Activating Token Index: 899

Text #17

Max Range: 0.0983. Min Range: -0.0983

Max Act: 0.0675. Min Act: -0.0003

Data Index: 967353 (C4 (Web Text))

Max Activating Token Index: 814

Text #18

Max Range: 0.0983. Min Range: -0.0983

Max Act: 0.0671. Min Act: -0.0003

Data Index: 1000769 (C4 (Web Text))

Max Activating Token Index: 114

Text #19

Max Range: 0.0983. Min Range: -0.0983

Max Act: 0.0669. Min Act: -0.0003

Data Index: 692307 (C4 (Web Text))

Max Activating Token Index: 397