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

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

Neuron 1663 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: 0.0908. Min Range: -0.0908

Max Act: 0.0908. Min Act: -0.0003

Data Index: 472018 (C4 (Web Text))

Max Activating Token Index: 150

Text #1

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0752. Min Act: -0.0002

Data Index: 75121 (C4 (Web Text))

Max Activating Token Index: 411

Text #2

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0761. Min Act: -0.0003

Data Index: 711566 (C4 (Web Text))

Max Activating Token Index: 455

Text #3

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0723. Min Act: -0.0003

Data Index: 633962 (C4 (Web Text))

Max Activating Token Index: 58

Text #4

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0717. Min Act: -0.0002

Data Index: 182205 (C4 (Web Text))

Max Activating Token Index: 40

Text #5

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0682. Min Act: -0.0003

Data Index: 130486 (C4 (Web Text))

Max Activating Token Index: 965

Text #6

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0658. Min Act: -0.0003

Data Index: 1085494 (C4 (Web Text))

Max Activating Token Index: 31

Text #7

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0656. Min Act: -0.0002

Data Index: 377692 (C4 (Web Text))

Max Activating Token Index: 63

Text #8

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0656. Min Act: -0.0002

Data Index: 10581 (C4 (Web Text))

Max Activating Token Index: 586

Text #9

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0670. Min Act: -0.0003

Data Index: 418980 (C4 (Web Text))

Max Activating Token Index: 280

Text #10

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0647. Min Act: -0.0002

Data Index: 649261 (C4 (Web Text))

Max Activating Token Index: 586

Text #11

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0608. Min Act: -0.0003

Data Index: 627682 (C4 (Web Text))

Max Activating Token Index: 76

Text #12

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0607. Min Act: -0.0002

Data Index: 62580 (C4 (Web Text))

Max Activating Token Index: 10

Text #13

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0597. Min Act: -0.0003

Data Index: 201470 (C4 (Web Text))

Max Activating Token Index: 406

Text #14

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0598. Min Act: -0.0003

Data Index: 114715 (C4 (Web Text))

Max Activating Token Index: 170

Text #15

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0571. Min Act: -0.0002

Data Index: 1194618 (C4 (Web Text))

Max Activating Token Index: 241

Text #16

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0578. Min Act: -0.0002

Data Index: 996172 (C4 (Web Text))

Max Activating Token Index: 252

Text #17

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0577. Min Act: -0.0002

Data Index: 104493 (C4 (Web Text))

Max Activating Token Index: 494

Text #18

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0594. Min Act: -0.0003

Data Index: 966528 (C4 (Web Text))

Max Activating Token Index: 933

Text #19

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0564. Min Act: -0.0003

Data Index: 365343 (C4 (Web Text))

Max Activating Token Index: 175