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

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

Neuron 1936 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5502. Min Range: -0.5502

Max Act: 0.5502. Min Act: -0.0003

Data Index: 262612 (C4 (Web Text))

Max Activating Token Index: 563

Text #1

Max Range: 0.5502. Min Range: -0.5502

Max Act: 0.4877. Min Act: -0.0002

Data Index: 238185 (C4 (Web Text))

Max Activating Token Index: 311

Text #2

Max Range: 0.5502. Min Range: -0.5502

Max Act: 0.5038. Min Act: -0.0002

Data Index: 68717 (C4 (Web Text))

Max Activating Token Index: 482

Text #3

Max Range: 0.5502. Min Range: -0.5502

Max Act: 0.5193. Min Act: -0.0002

Data Index: 284858 (C4 (Web Text))

Max Activating Token Index: 126

Text #4

Max Range: 0.5502. Min Range: -0.5502

Max Act: 0.4696. Min Act: -0.0003

Data Index: 685292 (C4 (Web Text))

Max Activating Token Index: 538

Text #5

Max Range: 0.5502. Min Range: -0.5502

Max Act: 0.5047. Min Act: -0.0003

Data Index: 820187 (C4 (Web Text))

Max Activating Token Index: 278

Text #6

Max Range: 0.5502. Min Range: -0.5502

Max Act: 0.4944. Min Act: -0.0003

Data Index: 612180 (C4 (Web Text))

Max Activating Token Index: 420

Text #7

Max Range: 0.5502. Min Range: -0.5502

Max Act: 0.4936. Min Act: -0.0003

Data Index: 358718 (C4 (Web Text))

Max Activating Token Index: 866

Text #8

Max Range: 0.5502. Min Range: -0.5502

Max Act: 0.4909. Min Act: -0.0002

Data Index: 778769 (C4 (Web Text))

Max Activating Token Index: 964

Text #9

Max Range: 0.5502. Min Range: -0.5502

Max Act: 0.5044. Min Act: -0.0002

Data Index: 897819 (C4 (Web Text))

Max Activating Token Index: 678

Text #10

Max Range: 0.5502. Min Range: -0.5502

Max Act: 0.4983. Min Act: -0.0003

Data Index: 1276878 (C4 (Web Text))

Max Activating Token Index: 65

Text #11

Max Range: 0.5502. Min Range: -0.5502

Max Act: 0.4655. Min Act: -0.0002

Data Index: 676256 (C4 (Web Text))

Max Activating Token Index: 328

Text #12

Max Range: 0.5502. Min Range: -0.5502

Max Act: 0.4811. Min Act: -0.0002

Data Index: 1187385 (C4 (Web Text))

Max Activating Token Index: 344

Text #13

Max Range: 0.5502. Min Range: -0.5502

Max Act: 0.4600. Min Act: -0.0003

Data Index: 754499 (C4 (Web Text))

Max Activating Token Index: 166

Text #14

Max Range: 0.5502. Min Range: -0.5502

Max Act: 0.4717. Min Act: -0.0002

Data Index: 13786 (C4 (Web Text))

Max Activating Token Index: 327

Text #15

Max Range: 0.5502. Min Range: -0.5502

Max Act: 0.4552. Min Act: -0.0003

Data Index: 116196 (C4 (Web Text))

Max Activating Token Index: 780

Text #16

Max Range: 0.5502. Min Range: -0.5502

Max Act: 0.4689. Min Act: -0.0003

Data Index: 1299055 (C4 (Web Text))

Max Activating Token Index: 350

Text #17

Max Range: 0.5502. Min Range: -0.5502

Max Act: 0.4355. Min Act: -0.0003

Data Index: 833006 (C4 (Web Text))

Max Activating Token Index: 155

Text #18

Max Range: 0.5502. Min Range: -0.5502

Max Act: 0.4809. Min Act: -0.0002

Data Index: 1019950 (C4 (Web Text))

Max Activating Token Index: 22

Text #19

Max Range: 0.5502. Min Range: -0.5502

Max Act: 0.4756. Min Act: -0.0003

Data Index: 1153365 (C4 (Web Text))

Max Activating Token Index: 686