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

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

Neuron 5668 in Layer 1

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: 0.0638. Min Range: -0.0638

Max Act: 0.0638. Min Act: -0.0002

Data Index: 874997 (C4 (Web Text))

Max Activating Token Index: 170

Text #1

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0603. Min Act: -0.0002

Data Index: 952543 (C4 (Web Text))

Max Activating Token Index: 874

Text #2

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0606. Min Act: -0.0002

Data Index: 957090 (C4 (Web Text))

Max Activating Token Index: 396

Text #3

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0607. Min Act: -0.0003

Data Index: 604743 (C4 (Web Text))

Max Activating Token Index: 769

Text #4

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0605. Min Act: -0.0002

Data Index: 1061685 (C4 (Web Text))

Max Activating Token Index: 6

Text #5

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0618. Min Act: -0.0002

Data Index: 1178550 (C4 (Web Text))

Max Activating Token Index: 145

Text #6

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0600. Min Act: -0.0003

Data Index: 785761 (C4 (Web Text))

Max Activating Token Index: 73

Text #7

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0594. Min Act: -0.0002

Data Index: 1171583 (C4 (Web Text))

Max Activating Token Index: 150

Text #8

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0604. Min Act: -0.0002

Data Index: 1122773 (C4 (Web Text))

Max Activating Token Index: 908

Text #9

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0591. Min Act: -0.0002

Data Index: 83274 (C4 (Web Text))

Max Activating Token Index: 112

Text #10

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0580. Min Act: -0.0002

Data Index: 163933 (C4 (Web Text))

Max Activating Token Index: 740

Text #11

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0586. Min Act: -0.0002

Data Index: 56994 (C4 (Web Text))

Max Activating Token Index: 145

Text #12

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0579. Min Act: -0.0002

Data Index: 1136807 (C4 (Web Text))

Max Activating Token Index: 111

Text #13

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0577. Min Act: -0.0002

Data Index: 620089 (C4 (Web Text))

Max Activating Token Index: 768

Text #14

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0604. Min Act: -0.0002

Data Index: 812214 (C4 (Web Text))

Max Activating Token Index: 194

Text #15

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0581. Min Act: -0.0002

Data Index: 1242033 (C4 (Web Text))

Max Activating Token Index: 304

Text #16

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0591. Min Act: -0.0002

Data Index: 964811 (C4 (Web Text))

Max Activating Token Index: 742

Text #17

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0589. Min Act: -0.0002

Data Index: 1256553 (C4 (Web Text))

Max Activating Token Index: 218

Text #18

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0583. Min Act: -0.0002

Data Index: 331484 (C4 (Web Text))

Max Activating Token Index: 322

Text #19

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0581. Min Act: -0.0003

Data Index: 1136439 (C4 (Web Text))

Max Activating Token Index: 375