Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3745 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0785. Min Act: -0.0001

Data Index: 963014 (C4 (Web Text))

Max Activating Token Index: 959

Text #1

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0727. Min Act: -0.0001

Data Index: 85290 (C4 (Web Text))

Max Activating Token Index: 398

Text #2

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0733. Min Act: -0.0001

Data Index: 986926 (C4 (Web Text))

Max Activating Token Index: 66

Text #3

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0728. Min Act: -0.0001

Data Index: 477951 (C4 (Web Text))

Max Activating Token Index: 48

Text #4

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0741. Min Act: -0.0001

Data Index: 1200617 (C4 (Web Text))

Max Activating Token Index: 712

Text #5

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0739. Min Act: -0.0001

Data Index: 1466031 (Python Code)

Max Activating Token Index: 365

Text #6

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0723. Min Act: -0.0001

Data Index: 697638 (C4 (Web Text))

Max Activating Token Index: 336

Text #7

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0736. Min Act: -0.0001

Data Index: 1487924 (Python Code)

Max Activating Token Index: 103

Text #8

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0725. Min Act: -0.0001

Data Index: 1623614 (Python Code)

Max Activating Token Index: 920

Text #9

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0721. Min Act: -0.0001

Data Index: 411136 (C4 (Web Text))

Max Activating Token Index: 220

Text #10

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0728. Min Act: -0.0001

Data Index: 15690 (C4 (Web Text))

Max Activating Token Index: 877

Text #11

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0710. Min Act: -0.0001

Data Index: 11566 (C4 (Web Text))

Max Activating Token Index: 28

Text #12

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0716. Min Act: -0.0001

Data Index: 1577902 (Python Code)

Max Activating Token Index: 306

Text #13

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0701. Min Act: -0.0001

Data Index: 647293 (C4 (Web Text))

Max Activating Token Index: 881

Text #14

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0727. Min Act: -0.0001

Data Index: 1599153 (Python Code)

Max Activating Token Index: 948

Text #15

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0709. Min Act: -0.0001

Data Index: 560989 (C4 (Web Text))

Max Activating Token Index: 747

Text #16

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0706. Min Act: -0.0001

Data Index: 843811 (C4 (Web Text))

Max Activating Token Index: 790

Text #17

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0710. Min Act: -0.0001

Data Index: 1200607 (C4 (Web Text))

Max Activating Token Index: 69

Text #18

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0701. Min Act: -0.0001

Data Index: 585454 (C4 (Web Text))

Max Activating Token Index: 186

Text #19

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0716. Min Act: -0.0001

Data Index: 708653 (C4 (Web Text))

Max Activating Token Index: 229