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

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

Neuron 5033 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7186. Min Range: -0.7186

Max Act: 0.7095. Min Act: -0.0000

Data Index: 1044567 (C4 (Web Text))

Max Activating Token Index: 48

Text #1

Max Range: 0.7186. Min Range: -0.7186

Max Act: 0.7186. Min Act: -0.0000

Data Index: 600404 (C4 (Web Text))

Max Activating Token Index: 363

Text #2

Max Range: 0.7186. Min Range: -0.7186

Max Act: 0.6379. Min Act: -0.0000

Data Index: 784415 (C4 (Web Text))

Max Activating Token Index: 467

Text #3

Max Range: 0.7186. Min Range: -0.7186

Max Act: 0.6605. Min Act: -0.0000

Data Index: 353988 (C4 (Web Text))

Max Activating Token Index: 707

Text #4

Max Range: 0.7186. Min Range: -0.7186

Max Act: 0.6414. Min Act: -0.0000

Data Index: 388902 (C4 (Web Text))

Max Activating Token Index: 725

Text #5

Max Range: 0.7186. Min Range: -0.7186

Max Act: 0.6015. Min Act: -0.0000

Data Index: 911171 (C4 (Web Text))

Max Activating Token Index: 333

Text #6

Max Range: 0.7186. Min Range: -0.7186

Max Act: 0.6480. Min Act: -0.0000

Data Index: 1294692 (C4 (Web Text))

Max Activating Token Index: 637

Text #7

Max Range: 0.7186. Min Range: -0.7186

Max Act: 0.6214. Min Act: -0.0000

Data Index: 1114514 (C4 (Web Text))

Max Activating Token Index: 777

Text #8

Max Range: 0.7186. Min Range: -0.7186

Max Act: 0.6266. Min Act: -0.0000

Data Index: 278252 (C4 (Web Text))

Max Activating Token Index: 605

Text #9

Max Range: 0.7186. Min Range: -0.7186

Max Act: 0.6072. Min Act: -0.0000

Data Index: 485877 (C4 (Web Text))

Max Activating Token Index: 126

Text #10

Max Range: 0.7186. Min Range: -0.7186

Max Act: 0.5749. Min Act: -0.0000

Data Index: 167731 (C4 (Web Text))

Max Activating Token Index: 750

Text #11

Max Range: 0.7186. Min Range: -0.7186

Max Act: 0.5830. Min Act: -0.0000

Data Index: 495029 (C4 (Web Text))

Max Activating Token Index: 1018

Text #12

Max Range: 0.7186. Min Range: -0.7186

Max Act: 0.6149. Min Act: -0.0000

Data Index: 358055 (C4 (Web Text))

Max Activating Token Index: 709

Text #13

Max Range: 0.7186. Min Range: -0.7186

Max Act: 0.6164. Min Act: -0.0000

Data Index: 1108747 (C4 (Web Text))

Max Activating Token Index: 831

Text #14

Max Range: 0.7186. Min Range: -0.7186

Max Act: 0.5715. Min Act: -0.0000

Data Index: 248726 (C4 (Web Text))

Max Activating Token Index: 970

Text #15

Max Range: 0.7186. Min Range: -0.7186

Max Act: 0.5512. Min Act: -0.0000

Data Index: 403103 (C4 (Web Text))

Max Activating Token Index: 441

Text #16

Max Range: 0.7186. Min Range: -0.7186

Max Act: 0.5851. Min Act: -0.0000

Data Index: 1231973 (C4 (Web Text))

Max Activating Token Index: 1015

Text #17

Max Range: 0.7186. Min Range: -0.7186

Max Act: 0.5813. Min Act: -0.0000

Data Index: 22741 (C4 (Web Text))

Max Activating Token Index: 473

Text #18

Max Range: 0.7186. Min Range: -0.7186

Max Act: 0.5495. Min Act: -0.0000

Data Index: 934243 (C4 (Web Text))

Max Activating Token Index: 329

Text #19

Max Range: 0.7186. Min Range: -0.7186

Max Act: 0.5280. Min Act: -0.0000

Data Index: 6889 (C4 (Web Text))

Max Activating Token Index: 125