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

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

Neuron 1364 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0731. Min Act: -0.0004

Data Index: 631964 (C4 (Web Text))

Max Activating Token Index: 267

Text #1

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0759. Min Act: -0.0004

Data Index: 126928 (C4 (Web Text))

Max Activating Token Index: 211

Text #2

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0774. Min Act: -0.0004

Data Index: 667652 (C4 (Web Text))

Max Activating Token Index: 578

Text #3

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0791. Min Act: -0.0004

Data Index: 759875 (C4 (Web Text))

Max Activating Token Index: 938

Text #4

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0669. Min Act: -0.0004

Data Index: 115222 (C4 (Web Text))

Max Activating Token Index: 894

Text #5

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0728. Min Act: -0.0004

Data Index: 1016136 (C4 (Web Text))

Max Activating Token Index: 585

Text #6

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0757. Min Act: -0.0004

Data Index: 767844 (C4 (Web Text))

Max Activating Token Index: 660

Text #7

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0723. Min Act: -0.0004

Data Index: 37615 (C4 (Web Text))

Max Activating Token Index: 341

Text #8

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0684. Min Act: -0.0004

Data Index: 308550 (C4 (Web Text))

Max Activating Token Index: 265

Text #9

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0810. Min Act: -0.0004

Data Index: 650816 (C4 (Web Text))

Max Activating Token Index: 667

Text #10

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0698. Min Act: -0.0004

Data Index: 39410 (C4 (Web Text))

Max Activating Token Index: 108

Text #11

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0661. Min Act: -0.0004

Data Index: 686734 (C4 (Web Text))

Max Activating Token Index: 334

Text #12

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0676. Min Act: -0.0004

Data Index: 730654 (C4 (Web Text))

Max Activating Token Index: 604

Text #13

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0647. Min Act: -0.0004

Data Index: 1348411 (C4 (Web Text))

Max Activating Token Index: 948

Text #14

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0659. Min Act: -0.0004

Data Index: 157074 (C4 (Web Text))

Max Activating Token Index: 535

Text #15

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0607. Min Act: -0.0004

Data Index: 1136506 (C4 (Web Text))

Max Activating Token Index: 787

Text #16

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0606. Min Act: -0.0004

Data Index: 773835 (C4 (Web Text))

Max Activating Token Index: 463

Text #17

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0577. Min Act: -0.0004

Data Index: 1222158 (C4 (Web Text))

Max Activating Token Index: 377

Text #18

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0649. Min Act: -0.0004

Data Index: 1239280 (C4 (Web Text))

Max Activating Token Index: 90

Text #19

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0675. Min Act: -0.0004

Data Index: 977526 (C4 (Web Text))

Max Activating Token Index: 960