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

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

Neuron 2492 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: 0.7044. Min Range: -0.7044

Max Act: 0.7044. Min Act: -0.0002

Data Index: 86676 (C4 (Web Text))

Max Activating Token Index: 275

Text #1

Max Range: 0.7044. Min Range: -0.7044

Max Act: 0.6318. Min Act: -0.0003

Data Index: 1136433 (C4 (Web Text))

Max Activating Token Index: 655

Text #2

Max Range: 0.7044. Min Range: -0.7044

Max Act: 0.6082. Min Act: -0.0002

Data Index: 1178944 (C4 (Web Text))

Max Activating Token Index: 264

Text #3

Max Range: 0.7044. Min Range: -0.7044

Max Act: 0.6047. Min Act: -0.0003

Data Index: 1075722 (C4 (Web Text))

Max Activating Token Index: 811

Text #4

Max Range: 0.7044. Min Range: -0.7044

Max Act: 0.6180. Min Act: -0.0002

Data Index: 1274080 (C4 (Web Text))

Max Activating Token Index: 668

Text #5

Max Range: 0.7044. Min Range: -0.7044

Max Act: 0.5978. Min Act: -0.0003

Data Index: 215605 (C4 (Web Text))

Max Activating Token Index: 931

Text #6

Max Range: 0.7044. Min Range: -0.7044

Max Act: 0.5958. Min Act: -0.0002

Data Index: 996443 (C4 (Web Text))

Max Activating Token Index: 673

Text #7

Max Range: 0.7044. Min Range: -0.7044

Max Act: 0.5638. Min Act: -0.0003

Data Index: 193331 (C4 (Web Text))

Max Activating Token Index: 622

Text #8

Max Range: 0.7044. Min Range: -0.7044

Max Act: 0.5315. Min Act: -0.0002

Data Index: 96840 (C4 (Web Text))

Max Activating Token Index: 381

Text #9

Max Range: 0.7044. Min Range: -0.7044

Max Act: 0.5288. Min Act: -0.0003

Data Index: 168291 (C4 (Web Text))

Max Activating Token Index: 721

Text #10

Max Range: 0.7044. Min Range: -0.7044

Max Act: 0.5219. Min Act: -0.0002

Data Index: 341895 (C4 (Web Text))

Max Activating Token Index: 122

Text #11

Max Range: 0.7044. Min Range: -0.7044

Max Act: 0.5324. Min Act: -0.0003

Data Index: 704542 (C4 (Web Text))

Max Activating Token Index: 626

Text #12

Max Range: 0.7044. Min Range: -0.7044

Max Act: 0.5266. Min Act: -0.0002

Data Index: 264557 (C4 (Web Text))

Max Activating Token Index: 196

Text #13

Max Range: 0.7044. Min Range: -0.7044

Max Act: 0.5116. Min Act: -0.0002

Data Index: 137612 (C4 (Web Text))

Max Activating Token Index: 479

Text #14

Max Range: 0.7044. Min Range: -0.7044

Max Act: 0.5066. Min Act: -0.0002

Data Index: 669815 (C4 (Web Text))

Max Activating Token Index: 724

Text #15

Max Range: 0.7044. Min Range: -0.7044

Max Act: 0.5048. Min Act: -0.0002

Data Index: 416190 (C4 (Web Text))

Max Activating Token Index: 794

Text #16

Max Range: 0.7044. Min Range: -0.7044

Max Act: 0.5143. Min Act: -0.0002

Data Index: 954192 (C4 (Web Text))

Max Activating Token Index: 571

Text #17

Max Range: 0.7044. Min Range: -0.7044

Max Act: 0.5113. Min Act: -0.0002

Data Index: 636556 (C4 (Web Text))

Max Activating Token Index: 332

Text #18

Max Range: 0.7044. Min Range: -0.7044

Max Act: 0.5141. Min Act: -0.0003

Data Index: 535882 (C4 (Web Text))

Max Activating Token Index: 746

Text #19

Max Range: 0.7044. Min Range: -0.7044

Max Act: 0.4928. Min Act: -0.0003

Data Index: 1358777 (C4 (Web Text))

Max Activating Token Index: 827