Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 41 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0765. Min Act: -0.0001

Data Index: 79891 (C4 (Web Text))

Max Activating Token Index: 426

Text #1

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0811. Min Act: -0.0001

Data Index: 1219705 (C4 (Web Text))

Max Activating Token Index: 597

Text #2

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0784. Min Act: -0.0001

Data Index: 9485 (C4 (Web Text))

Max Activating Token Index: 339

Text #3

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0656. Min Act: -0.0001

Data Index: 14906 (C4 (Web Text))

Max Activating Token Index: 918

Text #4

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0629. Min Act: -0.0001

Data Index: 757713 (C4 (Web Text))

Max Activating Token Index: 356

Text #5

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0691. Min Act: -0.0001

Data Index: 1144602 (C4 (Web Text))

Max Activating Token Index: 760

Text #6

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0603. Min Act: -0.0001

Data Index: 162801 (C4 (Web Text))

Max Activating Token Index: 426

Text #7

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0716. Min Act: -0.0001

Data Index: 954052 (C4 (Web Text))

Max Activating Token Index: 709

Text #8

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0663. Min Act: -0.0001

Data Index: 1279901 (C4 (Web Text))

Max Activating Token Index: 867

Text #9

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0637. Min Act: -0.0001

Data Index: 789392 (C4 (Web Text))

Max Activating Token Index: 855

Text #10

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0655. Min Act: -0.0001

Data Index: 1162304 (C4 (Web Text))

Max Activating Token Index: 923

Text #11

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0680. Min Act: -0.0001

Data Index: 760296 (C4 (Web Text))

Max Activating Token Index: 220

Text #12

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0598. Min Act: -0.0001

Data Index: 601818 (C4 (Web Text))

Max Activating Token Index: 511

Text #13

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0642. Min Act: -0.0001

Data Index: 646639 (C4 (Web Text))

Max Activating Token Index: 941

Text #14

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0636. Min Act: -0.0001

Data Index: 1209131 (C4 (Web Text))

Max Activating Token Index: 752

Text #15

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0628. Min Act: -0.0001

Data Index: 146690 (C4 (Web Text))

Max Activating Token Index: 32

Text #16

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0625. Min Act: -0.0001

Data Index: 1208064 (C4 (Web Text))

Max Activating Token Index: 398

Text #17

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0598. Min Act: -0.0001

Data Index: 385051 (C4 (Web Text))

Max Activating Token Index: 490

Text #18

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0672. Min Act: -0.0001

Data Index: 361362 (C4 (Web Text))

Max Activating Token Index: 408

Text #19

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0649. Min Act: -0.0001

Data Index: 966750 (C4 (Web Text))

Max Activating Token Index: 329