Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 136 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.2965. Min Range: -1.2965

Max Act: 1.2772. Min Act: -0.0002

Data Index: 1314805 (C4 (Web Text))

Max Activating Token Index: 903

Text #1

Max Range: 1.2965. Min Range: -1.2965

Max Act: 1.2965. Min Act: -0.0002

Data Index: 74099 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 1.2965. Min Range: -1.2965

Max Act: 1.1846. Min Act: -0.0001

Data Index: 268631 (C4 (Web Text))

Max Activating Token Index: 583

Text #3

Max Range: 1.2965. Min Range: -1.2965

Max Act: 1.1233. Min Act: -0.0002

Data Index: 82611 (C4 (Web Text))

Max Activating Token Index: 715

Text #4

Max Range: 1.2965. Min Range: -1.2965

Max Act: 1.1698. Min Act: -0.0001

Data Index: 721011 (C4 (Web Text))

Max Activating Token Index: 700

Text #5

Max Range: 1.2965. Min Range: -1.2965

Max Act: 1.1215. Min Act: -0.0002

Data Index: 773101 (C4 (Web Text))

Max Activating Token Index: 829

Text #6

Max Range: 1.2965. Min Range: -1.2965

Max Act: 1.1257. Min Act: -0.0001

Data Index: 1117552 (C4 (Web Text))

Max Activating Token Index: 240

Text #7

Max Range: 1.2965. Min Range: -1.2965

Max Act: 1.1211. Min Act: -0.0002

Data Index: 588409 (C4 (Web Text))

Max Activating Token Index: 36

Text #8

Max Range: 1.2965. Min Range: -1.2965

Max Act: 1.1884. Min Act: -0.0002

Data Index: 1154693 (C4 (Web Text))

Max Activating Token Index: 965

Text #9

Max Range: 1.2965. Min Range: -1.2965

Max Act: 1.1054. Min Act: -0.0001

Data Index: 1164844 (C4 (Web Text))

Max Activating Token Index: 399

Text #10

Max Range: 1.2965. Min Range: -1.2965

Max Act: 1.1290. Min Act: -0.0001

Data Index: 827781 (C4 (Web Text))

Max Activating Token Index: 266

Text #11

Max Range: 1.2965. Min Range: -1.2965

Max Act: 1.0844. Min Act: -0.0001

Data Index: 20585 (C4 (Web Text))

Max Activating Token Index: 818

Text #12

Max Range: 1.2965. Min Range: -1.2965

Max Act: 1.0284. Min Act: -0.0002

Data Index: 1249310 (C4 (Web Text))

Max Activating Token Index: 802

Text #13

Max Range: 1.2965. Min Range: -1.2965

Max Act: 1.0431. Min Act: -0.0001

Data Index: 1154837 (C4 (Web Text))

Max Activating Token Index: 83

Text #14

Max Range: 1.2965. Min Range: -1.2965

Max Act: 1.0606. Min Act: -0.0001

Data Index: 1220245 (C4 (Web Text))

Max Activating Token Index: 722

Text #15

Max Range: 1.2965. Min Range: -1.2965

Max Act: 0.9853. Min Act: -0.0002

Data Index: 729211 (C4 (Web Text))

Max Activating Token Index: 319

Text #16

Max Range: 1.2965. Min Range: -1.2965

Max Act: 1.0341. Min Act: -0.0002

Data Index: 1007947 (C4 (Web Text))

Max Activating Token Index: 446

Text #17

Max Range: 1.2965. Min Range: -1.2965

Max Act: 0.9704. Min Act: -0.0002

Data Index: 155860 (C4 (Web Text))

Max Activating Token Index: 460

Text #18

Max Range: 1.2965. Min Range: -1.2965

Max Act: 0.9977. Min Act: -0.0002

Data Index: 886794 (C4 (Web Text))

Max Activating Token Index: 33

Text #19

Max Range: 1.2965. Min Range: -1.2965

Max Act: 0.9925. Min Act: -0.0001

Data Index: 1117428 (C4 (Web Text))

Max Activating Token Index: 49