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

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

Neuron 3107 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5420. Min Range: -1.5420

Max Act: 1.5420. Min Act: -0.0000

Data Index: 1374330 (Python Code)

Max Activating Token Index: 811

Text #1

Max Range: 1.5420. Min Range: -1.5420

Max Act: 1.3734. Min Act: -0.0001

Data Index: 1654196 (Python Code)

Max Activating Token Index: 221

Text #2

Max Range: 1.5420. Min Range: -1.5420

Max Act: 1.3072. Min Act: -0.0000

Data Index: 938596 (C4 (Web Text))

Max Activating Token Index: 790

Text #3

Max Range: 1.5420. Min Range: -1.5420

Max Act: 1.3526. Min Act: -0.0000

Data Index: 533153 (C4 (Web Text))

Max Activating Token Index: 532

Text #4

Max Range: 1.5420. Min Range: -1.5420

Max Act: 1.2447. Min Act: -0.0001

Data Index: 1478171 (Python Code)

Max Activating Token Index: 353

Text #5

Max Range: 1.5420. Min Range: -1.5420

Max Act: 1.2331. Min Act: -0.0000

Data Index: 1156659 (C4 (Web Text))

Max Activating Token Index: 579

Text #6

Max Range: 1.5420. Min Range: -1.5420

Max Act: 1.2050. Min Act: -0.0000

Data Index: 422829 (C4 (Web Text))

Max Activating Token Index: 282

Text #7

Max Range: 1.5420. Min Range: -1.5420

Max Act: 1.1645. Min Act: -0.0000

Data Index: 591836 (C4 (Web Text))

Max Activating Token Index: 416

Text #8

Max Range: 1.5420. Min Range: -1.5420

Max Act: 1.1075. Min Act: -0.0000

Data Index: 757804 (C4 (Web Text))

Max Activating Token Index: 905

Text #9

Max Range: 1.5420. Min Range: -1.5420

Max Act: 1.1122. Min Act: -0.0000

Data Index: 1150353 (C4 (Web Text))

Max Activating Token Index: 203

Text #10

Max Range: 1.5420. Min Range: -1.5420

Max Act: 1.0829. Min Act: -0.0000

Data Index: 577223 (C4 (Web Text))

Max Activating Token Index: 12

Text #11

Max Range: 1.5420. Min Range: -1.5420

Max Act: 1.0982. Min Act: -0.0000

Data Index: 1310827 (C4 (Web Text))

Max Activating Token Index: 856

Text #12

Max Range: 1.5420. Min Range: -1.5420

Max Act: 1.0179. Min Act: -0.0000

Data Index: 352894 (C4 (Web Text))

Max Activating Token Index: 107

Text #13

Max Range: 1.5420. Min Range: -1.5420

Max Act: 0.9796. Min Act: -0.0000

Data Index: 610016 (C4 (Web Text))

Max Activating Token Index: 570

Text #14

Max Range: 1.5420. Min Range: -1.5420

Max Act: 1.0092. Min Act: -0.0000

Data Index: 25238 (C4 (Web Text))

Max Activating Token Index: 1013

Text #15

Max Range: 1.5420. Min Range: -1.5420

Max Act: 0.9101. Min Act: -0.0000

Data Index: 550703 (C4 (Web Text))

Max Activating Token Index: 353

Text #16

Max Range: 1.5420. Min Range: -1.5420

Max Act: 0.9805. Min Act: -0.0000

Data Index: 652769 (C4 (Web Text))

Max Activating Token Index: 723

Text #17

Max Range: 1.5420. Min Range: -1.5420

Max Act: 0.9723. Min Act: -0.0000

Data Index: 928791 (C4 (Web Text))

Max Activating Token Index: 590

Text #18

Max Range: 1.5420. Min Range: -1.5420

Max Act: 0.9229. Min Act: -0.0000

Data Index: 1649071 (Python Code)

Max Activating Token Index: 190

Text #19

Max Range: 1.5420. Min Range: -1.5420

Max Act: 0.9224. Min Act: -0.0000

Data Index: 1050468 (C4 (Web Text))

Max Activating Token Index: 901