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

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

Neuron 847 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8044. Min Range: -1.8044

Max Act: 1.8044. Min Act: -0.0000

Data Index: 587900 (C4 (Web Text))

Max Activating Token Index: 266

Text #1

Max Range: 1.8044. Min Range: -1.8044

Max Act: 1.7922. Min Act: -0.0000

Data Index: 81107 (C4 (Web Text))

Max Activating Token Index: 987

Text #2

Max Range: 1.8044. Min Range: -1.8044

Max Act: 1.2473. Min Act: -0.0000

Data Index: 537372 (C4 (Web Text))

Max Activating Token Index: 1001

Text #3

Max Range: 1.8044. Min Range: -1.8044

Max Act: 1.2597. Min Act: -0.0000

Data Index: 306082 (C4 (Web Text))

Max Activating Token Index: 89

Text #4

Max Range: 1.8044. Min Range: -1.8044

Max Act: 1.2048. Min Act: -0.0000

Data Index: 646863 (C4 (Web Text))

Max Activating Token Index: 153

Text #5

Max Range: 1.8044. Min Range: -1.8044

Max Act: 1.2767. Min Act: -0.0000

Data Index: 679624 (C4 (Web Text))

Max Activating Token Index: 180

Text #6

Max Range: 1.8044. Min Range: -1.8044

Max Act: 1.2275. Min Act: -0.0000

Data Index: 735353 (C4 (Web Text))

Max Activating Token Index: 152

Text #7

Max Range: 1.8044. Min Range: -1.8044

Max Act: 1.2622. Min Act: -0.0000

Data Index: 593835 (C4 (Web Text))

Max Activating Token Index: 256

Text #8

Max Range: 1.8044. Min Range: -1.8044

Max Act: 1.1826. Min Act: -0.0000

Data Index: 86878 (C4 (Web Text))

Max Activating Token Index: 53

Text #9

Max Range: 1.8044. Min Range: -1.8044

Max Act: 1.1866. Min Act: -0.0000

Data Index: 298512 (C4 (Web Text))

Max Activating Token Index: 314

Text #10

Max Range: 1.8044. Min Range: -1.8044

Max Act: 1.1074. Min Act: -0.0000

Data Index: 959914 (C4 (Web Text))

Max Activating Token Index: 299

Text #11

Max Range: 1.8044. Min Range: -1.8044

Max Act: 1.1177. Min Act: -0.0000

Data Index: 405316 (C4 (Web Text))

Max Activating Token Index: 306

Text #12

Max Range: 1.8044. Min Range: -1.8044

Max Act: 1.1159. Min Act: -0.0000

Data Index: 611614 (C4 (Web Text))

Max Activating Token Index: 297

Text #13

Max Range: 1.8044. Min Range: -1.8044

Max Act: 1.1147. Min Act: -0.0000

Data Index: 891143 (C4 (Web Text))

Max Activating Token Index: 756

Text #14

Max Range: 1.8044. Min Range: -1.8044

Max Act: 1.1167. Min Act: -0.0000

Data Index: 356549 (C4 (Web Text))

Max Activating Token Index: 756

Text #15

Max Range: 1.8044. Min Range: -1.8044

Max Act: 1.0747. Min Act: -0.0000

Data Index: 156176 (C4 (Web Text))

Max Activating Token Index: 193

Text #16

Max Range: 1.8044. Min Range: -1.8044

Max Act: 1.1036. Min Act: -0.0000

Data Index: 176087 (C4 (Web Text))

Max Activating Token Index: 63

Text #17

Max Range: 1.8044. Min Range: -1.8044

Max Act: 1.1936. Min Act: -0.0000

Data Index: 162843 (C4 (Web Text))

Max Activating Token Index: 1022

Text #18

Max Range: 1.8044. Min Range: -1.8044

Max Act: 1.2325. Min Act: -0.0000

Data Index: 894171 (C4 (Web Text))

Max Activating Token Index: 79

Text #19

Max Range: 1.8044. Min Range: -1.8044

Max Act: 1.1501. Min Act: -0.0000

Data Index: 288149 (C4 (Web Text))

Max Activating Token Index: 296