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

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

Neuron 563 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1740. Min Range: -1.1740

Max Act: 1.0634. Min Act: -0.0001

Data Index: 290429 (C4 (Web Text))

Max Activating Token Index: 877

Text #1

Max Range: 1.1740. Min Range: -1.1740

Max Act: 1.1740. Min Act: -0.0001

Data Index: 1232007 (C4 (Web Text))

Max Activating Token Index: 75

Text #2

Max Range: 1.1740. Min Range: -1.1740

Max Act: 0.9987. Min Act: -0.0001

Data Index: 965294 (C4 (Web Text))

Max Activating Token Index: 959

Text #3

Max Range: 1.1740. Min Range: -1.1740

Max Act: 1.0673. Min Act: -0.0001

Data Index: 92420 (C4 (Web Text))

Max Activating Token Index: 257

Text #4

Max Range: 1.1740. Min Range: -1.1740

Max Act: 1.0332. Min Act: -0.0001

Data Index: 195543 (C4 (Web Text))

Max Activating Token Index: 436

Text #5

Max Range: 1.1740. Min Range: -1.1740

Max Act: 0.9888. Min Act: -0.0001

Data Index: 212118 (C4 (Web Text))

Max Activating Token Index: 793

Text #6

Max Range: 1.1740. Min Range: -1.1740

Max Act: 0.9923. Min Act: -0.0001

Data Index: 765542 (C4 (Web Text))

Max Activating Token Index: 37

Text #7

Max Range: 1.1740. Min Range: -1.1740

Max Act: 0.9564. Min Act: -0.0001

Data Index: 678728 (C4 (Web Text))

Max Activating Token Index: 577

Text #8

Max Range: 1.1740. Min Range: -1.1740

Max Act: 0.9975. Min Act: -0.0001

Data Index: 26974 (C4 (Web Text))

Max Activating Token Index: 505

Text #9

Max Range: 1.1740. Min Range: -1.1740

Max Act: 0.9556. Min Act: -0.0001

Data Index: 941674 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 1.1740. Min Range: -1.1740

Max Act: 1.0074. Min Act: -0.0001

Data Index: 308337 (C4 (Web Text))

Max Activating Token Index: 341

Text #11

Max Range: 1.1740. Min Range: -1.1740

Max Act: 0.9738. Min Act: -0.0001

Data Index: 1066151 (C4 (Web Text))

Max Activating Token Index: 771

Text #12

Max Range: 1.1740. Min Range: -1.1740

Max Act: 0.9847. Min Act: -0.0001

Data Index: 151866 (C4 (Web Text))

Max Activating Token Index: 565

Text #13

Max Range: 1.1740. Min Range: -1.1740

Max Act: 0.9753. Min Act: -0.0001

Data Index: 1212900 (C4 (Web Text))

Max Activating Token Index: 278

Text #14

Max Range: 1.1740. Min Range: -1.1740

Max Act: 0.9510. Min Act: -0.0001

Data Index: 1254417 (C4 (Web Text))

Max Activating Token Index: 968

Text #15

Max Range: 1.1740. Min Range: -1.1740

Max Act: 0.9077. Min Act: -0.0001

Data Index: 150526 (C4 (Web Text))

Max Activating Token Index: 194

Text #16

Max Range: 1.1740. Min Range: -1.1740

Max Act: 0.9391. Min Act: -0.0001

Data Index: 226259 (C4 (Web Text))

Max Activating Token Index: 508

Text #17

Max Range: 1.1740. Min Range: -1.1740

Max Act: 0.9928. Min Act: -0.0001

Data Index: 364094 (C4 (Web Text))

Max Activating Token Index: 846

Text #18

Max Range: 1.1740. Min Range: -1.1740

Max Act: 0.9386. Min Act: -0.0001

Data Index: 349563 (C4 (Web Text))

Max Activating Token Index: 10

Text #19

Max Range: 1.1740. Min Range: -1.1740

Max Act: 0.9664. Min Act: -0.0001

Data Index: 1201861 (C4 (Web Text))

Max Activating Token Index: 644