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

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

Neuron 156 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.4797. Min Range: -1.4797

Max Act: 1.4797. Min Act: -0.0000

Data Index: 1244608 (C4 (Web Text))

Max Activating Token Index: 952

Text #1

Max Range: 1.4797. Min Range: -1.4797

Max Act: 1.3898. Min Act: -0.0000

Data Index: 345791 (C4 (Web Text))

Max Activating Token Index: 703

Text #2

Max Range: 1.4797. Min Range: -1.4797

Max Act: 1.2075. Min Act: -0.0000

Data Index: 880038 (C4 (Web Text))

Max Activating Token Index: 545

Text #3

Max Range: 1.4797. Min Range: -1.4797

Max Act: 1.1741. Min Act: -0.0000

Data Index: 558351 (C4 (Web Text))

Max Activating Token Index: 29

Text #4

Max Range: 1.4797. Min Range: -1.4797

Max Act: 1.1522. Min Act: -0.0000

Data Index: 509903 (C4 (Web Text))

Max Activating Token Index: 277

Text #5

Max Range: 1.4797. Min Range: -1.4797

Max Act: 1.1935. Min Act: -0.0000

Data Index: 817581 (C4 (Web Text))

Max Activating Token Index: 930

Text #6

Max Range: 1.4797. Min Range: -1.4797

Max Act: 1.1886. Min Act: -0.0000

Data Index: 335162 (C4 (Web Text))

Max Activating Token Index: 335

Text #7

Max Range: 1.4797. Min Range: -1.4797

Max Act: 1.0626. Min Act: -0.0000

Data Index: 1230917 (C4 (Web Text))

Max Activating Token Index: 420

Text #8

Max Range: 1.4797. Min Range: -1.4797

Max Act: 0.9944. Min Act: -0.0000

Data Index: 989433 (C4 (Web Text))

Max Activating Token Index: 983

Text #9

Max Range: 1.4797. Min Range: -1.4797

Max Act: 1.0244. Min Act: -0.0000

Data Index: 560171 (C4 (Web Text))

Max Activating Token Index: 718

Text #10

Max Range: 1.4797. Min Range: -1.4797

Max Act: 1.0747. Min Act: -0.0000

Data Index: 605267 (C4 (Web Text))

Max Activating Token Index: 987

Text #11

Max Range: 1.4797. Min Range: -1.4797

Max Act: 1.0783. Min Act: -0.0000

Data Index: 758916 (C4 (Web Text))

Max Activating Token Index: 240

Text #12

Max Range: 1.4797. Min Range: -1.4797

Max Act: 0.9978. Min Act: -0.0000

Data Index: 87074 (C4 (Web Text))

Max Activating Token Index: 611

Text #13

Max Range: 1.4797. Min Range: -1.4797

Max Act: 0.9859. Min Act: -0.0000

Data Index: 272158 (C4 (Web Text))

Max Activating Token Index: 957

Text #14

Max Range: 1.4797. Min Range: -1.4797

Max Act: 0.9435. Min Act: -0.0000

Data Index: 181819 (C4 (Web Text))

Max Activating Token Index: 609

Text #15

Max Range: 1.4797. Min Range: -1.4797

Max Act: 0.9719. Min Act: -0.0000

Data Index: 250949 (C4 (Web Text))

Max Activating Token Index: 645

Text #16

Max Range: 1.4797. Min Range: -1.4797

Max Act: 0.9704. Min Act: -0.0000

Data Index: 302692 (C4 (Web Text))

Max Activating Token Index: 744

Text #17

Max Range: 1.4797. Min Range: -1.4797

Max Act: 0.9608. Min Act: -0.0000

Data Index: 656356 (C4 (Web Text))

Max Activating Token Index: 285

Text #18

Max Range: 1.4797. Min Range: -1.4797

Max Act: 0.9489. Min Act: -0.0000

Data Index: 997741 (C4 (Web Text))

Max Activating Token Index: 372

Text #19

Max Range: 1.4797. Min Range: -1.4797

Max Act: 0.9375. Min Act: -0.0000

Data Index: 719971 (C4 (Web Text))

Max Activating Token Index: 199