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

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

Neuron 2158 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0767. Min Act: -0.0003

Data Index: 319351 (C4 (Web Text))

Max Activating Token Index: 577

Text #1

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0664. Min Act: -0.0003

Data Index: 605701 (C4 (Web Text))

Max Activating Token Index: 1001

Text #2

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0651. Min Act: -0.0003

Data Index: 270255 (C4 (Web Text))

Max Activating Token Index: 270

Text #3

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0597. Min Act: -0.0003

Data Index: 1297091 (C4 (Web Text))

Max Activating Token Index: 1007

Text #4

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0628. Min Act: -0.0003

Data Index: 1012093 (C4 (Web Text))

Max Activating Token Index: 208

Text #5

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0604. Min Act: -0.0003

Data Index: 1330797 (C4 (Web Text))

Max Activating Token Index: 123

Text #6

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0579. Min Act: -0.0003

Data Index: 822658 (C4 (Web Text))

Max Activating Token Index: 577

Text #7

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0623. Min Act: -0.0003

Data Index: 927594 (C4 (Web Text))

Max Activating Token Index: 905

Text #8

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0572. Min Act: -0.0003

Data Index: 141884 (C4 (Web Text))

Max Activating Token Index: 259

Text #9

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0642. Min Act: -0.0003

Data Index: 628249 (C4 (Web Text))

Max Activating Token Index: 332

Text #10

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0545. Min Act: -0.0003

Data Index: 1273326 (C4 (Web Text))

Max Activating Token Index: 976

Text #11

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0490. Min Act: -0.0003

Data Index: 325107 (C4 (Web Text))

Max Activating Token Index: 590

Text #12

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0492. Min Act: -0.0003

Data Index: 1108640 (C4 (Web Text))

Max Activating Token Index: 638

Text #13

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0563. Min Act: -0.0003

Data Index: 345288 (C4 (Web Text))

Max Activating Token Index: 205

Text #14

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0579. Min Act: -0.0003

Data Index: 916183 (C4 (Web Text))

Max Activating Token Index: 73

Text #15

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0540. Min Act: -0.0003

Data Index: 1047442 (C4 (Web Text))

Max Activating Token Index: 605

Text #16

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0515. Min Act: -0.0003

Data Index: 992391 (C4 (Web Text))

Max Activating Token Index: 742

Text #17

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0534. Min Act: -0.0003

Data Index: 688889 (C4 (Web Text))

Max Activating Token Index: 163

Text #18

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0524. Min Act: -0.0003

Data Index: 690653 (C4 (Web Text))

Max Activating Token Index: 954

Text #19

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0518. Min Act: -0.0003

Data Index: 771489 (C4 (Web Text))

Max Activating Token Index: 760