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

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

Neuron 3805 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0775. Min Act: -0.0003

Data Index: 206908 (C4 (Web Text))

Max Activating Token Index: 189

Text #1

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0673. Min Act: -0.0003

Data Index: 596906 (C4 (Web Text))

Max Activating Token Index: 950

Text #2

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0685. Min Act: -0.0003

Data Index: 569646 (C4 (Web Text))

Max Activating Token Index: 30

Text #3

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0684. Min Act: -0.0003

Data Index: 250011 (C4 (Web Text))

Max Activating Token Index: 803

Text #4

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0631. Min Act: -0.0003

Data Index: 563943 (C4 (Web Text))

Max Activating Token Index: 311

Text #5

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0602. Min Act: -0.0002

Data Index: 1227458 (C4 (Web Text))

Max Activating Token Index: 83

Text #6

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0605. Min Act: -0.0003

Data Index: 955544 (C4 (Web Text))

Max Activating Token Index: 352

Text #7

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0603. Min Act: -0.0003

Data Index: 773627 (C4 (Web Text))

Max Activating Token Index: 226

Text #8

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0597. Min Act: -0.0003

Data Index: 861501 (C4 (Web Text))

Max Activating Token Index: 497

Text #9

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0583. Min Act: -0.0003

Data Index: 674288 (C4 (Web Text))

Max Activating Token Index: 148

Text #10

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0565. Min Act: -0.0003

Data Index: 622816 (C4 (Web Text))

Max Activating Token Index: 275

Text #11

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0544. Min Act: -0.0003

Data Index: 767692 (C4 (Web Text))

Max Activating Token Index: 155

Text #12

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0550. Min Act: -0.0003

Data Index: 530119 (C4 (Web Text))

Max Activating Token Index: 409

Text #13

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0541. Min Act: -0.0003

Data Index: 996344 (C4 (Web Text))

Max Activating Token Index: 864

Text #14

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0551. Min Act: -0.0003

Data Index: 667316 (C4 (Web Text))

Max Activating Token Index: 169

Text #15

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0541. Min Act: -0.0003

Data Index: 1102284 (C4 (Web Text))

Max Activating Token Index: 311

Text #16

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0537. Min Act: -0.0003

Data Index: 391684 (C4 (Web Text))

Max Activating Token Index: 212

Text #17

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0576. Min Act: -0.0003

Data Index: 302949 (C4 (Web Text))

Max Activating Token Index: 391

Text #18

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0554. Min Act: -0.0003

Data Index: 407737 (C4 (Web Text))

Max Activating Token Index: 186

Text #19

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0578. Min Act: -0.0003

Data Index: 8720 (C4 (Web Text))

Max Activating Token Index: 195