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

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

Neuron 5920 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.2171. Min Range: -1.2171

Max Act: 1.2171. Min Act: -0.0002

Data Index: 65135 (C4 (Web Text))

Max Activating Token Index: 107

Text #1

Max Range: 1.2171. Min Range: -1.2171

Max Act: 1.1625. Min Act: -0.0002

Data Index: 478698 (C4 (Web Text))

Max Activating Token Index: 284

Text #2

Max Range: 1.2171. Min Range: -1.2171

Max Act: 1.0838. Min Act: -0.0002

Data Index: 1148447 (C4 (Web Text))

Max Activating Token Index: 200

Text #3

Max Range: 1.2171. Min Range: -1.2171

Max Act: 1.1219. Min Act: -0.0002

Data Index: 52552 (C4 (Web Text))

Max Activating Token Index: 116

Text #4

Max Range: 1.2171. Min Range: -1.2171

Max Act: 1.0971. Min Act: -0.0002

Data Index: 798957 (C4 (Web Text))

Max Activating Token Index: 197

Text #5

Max Range: 1.2171. Min Range: -1.2171

Max Act: 1.1013. Min Act: -0.0002

Data Index: 1105612 (C4 (Web Text))

Max Activating Token Index: 162

Text #6

Max Range: 1.2171. Min Range: -1.2171

Max Act: 1.0878. Min Act: -0.0002

Data Index: 163154 (C4 (Web Text))

Max Activating Token Index: 226

Text #7

Max Range: 1.2171. Min Range: -1.2171

Max Act: 1.0576. Min Act: -0.0002

Data Index: 199862 (C4 (Web Text))

Max Activating Token Index: 72

Text #8

Max Range: 1.2171. Min Range: -1.2171

Max Act: 1.0394. Min Act: -0.0002

Data Index: 126221 (C4 (Web Text))

Max Activating Token Index: 81

Text #9

Max Range: 1.2171. Min Range: -1.2171

Max Act: 1.0608. Min Act: -0.0002

Data Index: 532747 (C4 (Web Text))

Max Activating Token Index: 104

Text #10

Max Range: 1.2171. Min Range: -1.2171

Max Act: 1.0460. Min Act: -0.0002

Data Index: 446507 (C4 (Web Text))

Max Activating Token Index: 91

Text #11

Max Range: 1.2171. Min Range: -1.2171

Max Act: 1.0309. Min Act: -0.0002

Data Index: 345757 (C4 (Web Text))

Max Activating Token Index: 66

Text #12

Max Range: 1.2171. Min Range: -1.2171

Max Act: 1.0143. Min Act: -0.0002

Data Index: 383907 (C4 (Web Text))

Max Activating Token Index: 376

Text #13

Max Range: 1.2171. Min Range: -1.2171

Max Act: 0.9929. Min Act: -0.0002

Data Index: 483050 (C4 (Web Text))

Max Activating Token Index: 207

Text #14

Max Range: 1.2171. Min Range: -1.2171

Max Act: 1.0007. Min Act: -0.0002

Data Index: 738017 (C4 (Web Text))

Max Activating Token Index: 809

Text #15

Max Range: 1.2171. Min Range: -1.2171

Max Act: 0.9904. Min Act: -0.0002

Data Index: 46287 (C4 (Web Text))

Max Activating Token Index: 101

Text #16

Max Range: 1.2171. Min Range: -1.2171

Max Act: 1.0186. Min Act: -0.0002

Data Index: 880856 (C4 (Web Text))

Max Activating Token Index: 270

Text #17

Max Range: 1.2171. Min Range: -1.2171

Max Act: 1.0523. Min Act: -0.0002

Data Index: 320914 (C4 (Web Text))

Max Activating Token Index: 324

Text #18

Max Range: 1.2171. Min Range: -1.2171

Max Act: 1.0238. Min Act: -0.0002

Data Index: 666547 (C4 (Web Text))

Max Activating Token Index: 870

Text #19

Max Range: 1.2171. Min Range: -1.2171

Max Act: 1.0099. Min Act: -0.0002

Data Index: 177838 (C4 (Web Text))

Max Activating Token Index: 217