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

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

Neuron 3604 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0619. Min Act: -0.0002

Data Index: 816917 (C4 (Web Text))

Max Activating Token Index: 189

Text #1

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0580. Min Act: -0.0002

Data Index: 39948 (C4 (Web Text))

Max Activating Token Index: 127

Text #2

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0573. Min Act: -0.0002

Data Index: 486025 (C4 (Web Text))

Max Activating Token Index: 508

Text #3

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0521. Min Act: -0.0002

Data Index: 1149666 (C4 (Web Text))

Max Activating Token Index: 638

Text #4

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0519. Min Act: -0.0002

Data Index: 1029381 (C4 (Web Text))

Max Activating Token Index: 555

Text #5

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0515. Min Act: -0.0002

Data Index: 825822 (C4 (Web Text))

Max Activating Token Index: 136

Text #6

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0497. Min Act: -0.0002

Data Index: 724670 (C4 (Web Text))

Max Activating Token Index: 869

Text #7

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0496. Min Act: -0.0001

Data Index: 475775 (C4 (Web Text))

Max Activating Token Index: 140

Text #8

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0494. Min Act: -0.0002

Data Index: 834946 (C4 (Web Text))

Max Activating Token Index: 155

Text #9

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0491. Min Act: -0.0002

Data Index: 104735 (C4 (Web Text))

Max Activating Token Index: 368

Text #10

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0489. Min Act: -0.0002

Data Index: 579774 (C4 (Web Text))

Max Activating Token Index: 946

Text #11

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0487. Min Act: -0.0002

Data Index: 1189177 (C4 (Web Text))

Max Activating Token Index: 801

Text #12

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0486. Min Act: -0.0002

Data Index: 800195 (C4 (Web Text))

Max Activating Token Index: 436

Text #13

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0485. Min Act: -0.0002

Data Index: 961149 (C4 (Web Text))

Max Activating Token Index: 869

Text #14

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0470. Min Act: -0.0002

Data Index: 89018 (C4 (Web Text))

Max Activating Token Index: 197

Text #15

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0467. Min Act: -0.0001

Data Index: 642921 (C4 (Web Text))

Max Activating Token Index: 511

Text #16

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0465. Min Act: -0.0002

Data Index: 117912 (C4 (Web Text))

Max Activating Token Index: 650

Text #17

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0457. Min Act: -0.0002

Data Index: 1223186 (C4 (Web Text))

Max Activating Token Index: 346

Text #18

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0456. Min Act: -0.0002

Data Index: 1244268 (C4 (Web Text))

Max Activating Token Index: 143

Text #19

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0456. Min Act: -0.0002

Data Index: 264156 (C4 (Web Text))

Max Activating Token Index: 146