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

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

Neuron 1152 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9807. Min Range: -2.9807

Max Act: 2.8390. Min Act: -0.0000

Data Index: 115777 (C4 (Web Text))

Max Activating Token Index: 214

Text #1

Max Range: 2.9807. Min Range: -2.9807

Max Act: 2.9807. Min Act: -0.0000

Data Index: 1163679 (C4 (Web Text))

Max Activating Token Index: 165

Text #2

Max Range: 2.9807. Min Range: -2.9807

Max Act: 2.6072. Min Act: -0.0000

Data Index: 852779 (C4 (Web Text))

Max Activating Token Index: 30

Text #3

Max Range: 2.9807. Min Range: -2.9807

Max Act: 2.2464. Min Act: -0.0000

Data Index: 722366 (C4 (Web Text))

Max Activating Token Index: 633

Text #4

Max Range: 2.9807. Min Range: -2.9807

Max Act: 2.2156. Min Act: -0.0000

Data Index: 463748 (C4 (Web Text))

Max Activating Token Index: 604

Text #5

Max Range: 2.9807. Min Range: -2.9807

Max Act: 2.1636. Min Act: -0.0000

Data Index: 176899 (C4 (Web Text))

Max Activating Token Index: 619

Text #6

Max Range: 2.9807. Min Range: -2.9807

Max Act: 2.1580. Min Act: -0.0000

Data Index: 352526 (C4 (Web Text))

Max Activating Token Index: 529

Text #7

Max Range: 2.9807. Min Range: -2.9807

Max Act: 2.1392. Min Act: -0.0000

Data Index: 1025254 (C4 (Web Text))

Max Activating Token Index: 409

Text #8

Max Range: 2.9807. Min Range: -2.9807

Max Act: 2.1203. Min Act: -0.0000

Data Index: 1146961 (C4 (Web Text))

Max Activating Token Index: 51

Text #9

Max Range: 2.9807. Min Range: -2.9807

Max Act: 2.1068. Min Act: -0.0000

Data Index: 35276 (C4 (Web Text))

Max Activating Token Index: 145

Text #10

Max Range: 2.9807. Min Range: -2.9807

Max Act: 2.0769. Min Act: -0.0000

Data Index: 486346 (C4 (Web Text))

Max Activating Token Index: 707

Text #11

Max Range: 2.9807. Min Range: -2.9807

Max Act: 2.0333. Min Act: -0.0000

Data Index: 758346 (C4 (Web Text))

Max Activating Token Index: 835

Text #12

Max Range: 2.9807. Min Range: -2.9807

Max Act: 2.0131. Min Act: -0.0000

Data Index: 1616226 (Python Code)

Max Activating Token Index: 446

Text #13

Max Range: 2.9807. Min Range: -2.9807

Max Act: 2.0049. Min Act: -0.0000

Data Index: 143227 (C4 (Web Text))

Max Activating Token Index: 978

Text #14

Max Range: 2.9807. Min Range: -2.9807

Max Act: 1.9726. Min Act: -0.0000

Data Index: 1249958 (C4 (Web Text))

Max Activating Token Index: 458

Text #15

Max Range: 2.9807. Min Range: -2.9807

Max Act: 1.9198. Min Act: -0.0000

Data Index: 1035567 (C4 (Web Text))

Max Activating Token Index: 430

Text #16

Max Range: 2.9807. Min Range: -2.9807

Max Act: 1.8816. Min Act: -0.0000

Data Index: 395738 (C4 (Web Text))

Max Activating Token Index: 461

Text #17

Max Range: 2.9807. Min Range: -2.9807

Max Act: 1.9518. Min Act: -0.0000

Data Index: 1038961 (C4 (Web Text))

Max Activating Token Index: 743

Text #18

Max Range: 2.9807. Min Range: -2.9807

Max Act: 1.6483. Min Act: -0.0000

Data Index: 930283 (C4 (Web Text))

Max Activating Token Index: 272

Text #19

Max Range: 2.9807. Min Range: -2.9807

Max Act: 1.9196. Min Act: -0.0000

Data Index: 696159 (C4 (Web Text))

Max Activating Token Index: 299