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

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

Neuron 3527 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: 1.9176. Min Range: -1.9176

Max Act: 1.9176. Min Act: -0.0002

Data Index: 1217486 (C4 (Web Text))

Max Activating Token Index: 455

Text #1

Max Range: 1.9176. Min Range: -1.9176

Max Act: 1.7086. Min Act: -0.0002

Data Index: 1073289 (C4 (Web Text))

Max Activating Token Index: 291

Text #2

Max Range: 1.9176. Min Range: -1.9176

Max Act: 1.6812. Min Act: -0.0002

Data Index: 1106283 (C4 (Web Text))

Max Activating Token Index: 556

Text #3

Max Range: 1.9176. Min Range: -1.9176

Max Act: 1.6973. Min Act: -0.0002

Data Index: 1186492 (C4 (Web Text))

Max Activating Token Index: 869

Text #4

Max Range: 1.9176. Min Range: -1.9176

Max Act: 1.6993. Min Act: -0.0002

Data Index: 731966 (C4 (Web Text))

Max Activating Token Index: 786

Text #5

Max Range: 1.9176. Min Range: -1.9176

Max Act: 1.6896. Min Act: -0.0002

Data Index: 475631 (C4 (Web Text))

Max Activating Token Index: 25

Text #6

Max Range: 1.9176. Min Range: -1.9176

Max Act: 1.6806. Min Act: -0.0003

Data Index: 280497 (C4 (Web Text))

Max Activating Token Index: 138

Text #7

Max Range: 1.9176. Min Range: -1.9176

Max Act: 1.6123. Min Act: -0.0002

Data Index: 145990 (C4 (Web Text))

Max Activating Token Index: 505

Text #8

Max Range: 1.9176. Min Range: -1.9176

Max Act: 1.6072. Min Act: -0.0002

Data Index: 428010 (C4 (Web Text))

Max Activating Token Index: 18

Text #9

Max Range: 1.9176. Min Range: -1.9176

Max Act: 1.6230. Min Act: -0.0002

Data Index: 547577 (C4 (Web Text))

Max Activating Token Index: 63

Text #10

Max Range: 1.9176. Min Range: -1.9176

Max Act: 1.5652. Min Act: -0.0002

Data Index: 957234 (C4 (Web Text))

Max Activating Token Index: 299

Text #11

Max Range: 1.9176. Min Range: -1.9176

Max Act: 1.5734. Min Act: -0.0003

Data Index: 1237585 (C4 (Web Text))

Max Activating Token Index: 861

Text #12

Max Range: 1.9176. Min Range: -1.9176

Max Act: 1.5798. Min Act: -0.0002

Data Index: 342927 (C4 (Web Text))

Max Activating Token Index: 974

Text #13

Max Range: 1.9176. Min Range: -1.9176

Max Act: 1.6030. Min Act: -0.0002

Data Index: 36636 (C4 (Web Text))

Max Activating Token Index: 285

Text #14

Max Range: 1.9176. Min Range: -1.9176

Max Act: 1.5560. Min Act: -0.0002

Data Index: 518481 (C4 (Web Text))

Max Activating Token Index: 689

Text #15

Max Range: 1.9176. Min Range: -1.9176

Max Act: 1.5438. Min Act: -0.0002

Data Index: 179035 (C4 (Web Text))

Max Activating Token Index: 778

Text #16

Max Range: 1.9176. Min Range: -1.9176

Max Act: 1.5806. Min Act: -0.0003

Data Index: 1162584 (C4 (Web Text))

Max Activating Token Index: 693

Text #17

Max Range: 1.9176. Min Range: -1.9176

Max Act: 1.5585. Min Act: -0.0002

Data Index: 220484 (C4 (Web Text))

Max Activating Token Index: 520

Text #18

Max Range: 1.9176. Min Range: -1.9176

Max Act: 1.6006. Min Act: -0.0002

Data Index: 213934 (C4 (Web Text))

Max Activating Token Index: 14

Text #19

Max Range: 1.9176. Min Range: -1.9176

Max Act: 1.5159. Min Act: -0.0002

Data Index: 1206089 (C4 (Web Text))

Max Activating Token Index: 2