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

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

Neuron 102 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: 2.2687. Min Range: -2.2687

Max Act: 2.2687. Min Act: -0.0002

Data Index: 555915 (C4 (Web Text))

Max Activating Token Index: 196

Text #1

Max Range: 2.2687. Min Range: -2.2687

Max Act: 2.2633. Min Act: -0.0003

Data Index: 625392 (C4 (Web Text))

Max Activating Token Index: 92

Text #2

Max Range: 2.2687. Min Range: -2.2687

Max Act: 2.1601. Min Act: -0.0002

Data Index: 465855 (C4 (Web Text))

Max Activating Token Index: 104

Text #3

Max Range: 2.2687. Min Range: -2.2687

Max Act: 2.1326. Min Act: -0.0002

Data Index: 1177572 (C4 (Web Text))

Max Activating Token Index: 783

Text #4

Max Range: 2.2687. Min Range: -2.2687

Max Act: 2.0251. Min Act: -0.0002

Data Index: 137911 (C4 (Web Text))

Max Activating Token Index: 663

Text #5

Max Range: 2.2687. Min Range: -2.2687

Max Act: 1.9966. Min Act: -0.0003

Data Index: 1200792 (C4 (Web Text))

Max Activating Token Index: 119

Text #6

Max Range: 2.2687. Min Range: -2.2687

Max Act: 1.9725. Min Act: -0.0002

Data Index: 149921 (C4 (Web Text))

Max Activating Token Index: 248

Text #7

Max Range: 2.2687. Min Range: -2.2687

Max Act: 1.9958. Min Act: -0.0002

Data Index: 356423 (C4 (Web Text))

Max Activating Token Index: 667

Text #8

Max Range: 2.2687. Min Range: -2.2687

Max Act: 1.9705. Min Act: -0.0002

Data Index: 646942 (C4 (Web Text))

Max Activating Token Index: 292

Text #9

Max Range: 2.2687. Min Range: -2.2687

Max Act: 1.9294. Min Act: -0.0003

Data Index: 21157 (C4 (Web Text))

Max Activating Token Index: 867

Text #10

Max Range: 2.2687. Min Range: -2.2687

Max Act: 1.9781. Min Act: -0.0002

Data Index: 143170 (C4 (Web Text))

Max Activating Token Index: 471

Text #11

Max Range: 2.2687. Min Range: -2.2687

Max Act: 1.9139. Min Act: -0.0002

Data Index: 778560 (C4 (Web Text))

Max Activating Token Index: 132

Text #12

Max Range: 2.2687. Min Range: -2.2687

Max Act: 1.8909. Min Act: -0.0002

Data Index: 555733 (C4 (Web Text))

Max Activating Token Index: 372

Text #13

Max Range: 2.2687. Min Range: -2.2687

Max Act: 1.9202. Min Act: -0.0002

Data Index: 1342821 (C4 (Web Text))

Max Activating Token Index: 216

Text #14

Max Range: 2.2687. Min Range: -2.2687

Max Act: 1.8996. Min Act: -0.0002

Data Index: 1268836 (C4 (Web Text))

Max Activating Token Index: 312

Text #15

Max Range: 2.2687. Min Range: -2.2687

Max Act: 1.9074. Min Act: -0.0002

Data Index: 695451 (C4 (Web Text))

Max Activating Token Index: 905

Text #16

Max Range: 2.2687. Min Range: -2.2687

Max Act: 1.9082. Min Act: -0.0002

Data Index: 264839 (C4 (Web Text))

Max Activating Token Index: 54

Text #17

Max Range: 2.2687. Min Range: -2.2687

Max Act: 1.8784. Min Act: -0.0002

Data Index: 208598 (C4 (Web Text))

Max Activating Token Index: 830

Text #18

Max Range: 2.2687. Min Range: -2.2687

Max Act: 1.8637. Min Act: -0.0002

Data Index: 1287620 (C4 (Web Text))

Max Activating Token Index: 156

Text #19

Max Range: 2.2687. Min Range: -2.2687

Max Act: 1.8178. Min Act: -0.0002

Data Index: 268966 (C4 (Web Text))

Max Activating Token Index: 282