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

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

Neuron 2583 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.1338. Min Range: -3.1338

Max Act: 2.8681. Min Act: -0.0000

Data Index: 1307852 (C4 (Web Text))

Max Activating Token Index: 363

Text #1

Max Range: 3.1338. Min Range: -3.1338

Max Act: 3.1338. Min Act: -0.0000

Data Index: 107524 (C4 (Web Text))

Max Activating Token Index: 481

Text #2

Max Range: 3.1338. Min Range: -3.1338

Max Act: 2.8779. Min Act: -0.0000

Data Index: 1112308 (C4 (Web Text))

Max Activating Token Index: 610

Text #3

Max Range: 3.1338. Min Range: -3.1338

Max Act: 2.8284. Min Act: -0.0000

Data Index: 810597 (C4 (Web Text))

Max Activating Token Index: 309

Text #4

Max Range: 3.1338. Min Range: -3.1338

Max Act: 2.8257. Min Act: -0.0000

Data Index: 501377 (C4 (Web Text))

Max Activating Token Index: 586

Text #5

Max Range: 3.1338. Min Range: -3.1338

Max Act: 2.6656. Min Act: -0.0000

Data Index: 495431 (C4 (Web Text))

Max Activating Token Index: 943

Text #6

Max Range: 3.1338. Min Range: -3.1338

Max Act: 2.8981. Min Act: -0.0000

Data Index: 324789 (C4 (Web Text))

Max Activating Token Index: 527

Text #7

Max Range: 3.1338. Min Range: -3.1338

Max Act: 2.5436. Min Act: -0.0000

Data Index: 1027166 (C4 (Web Text))

Max Activating Token Index: 867

Text #8

Max Range: 3.1338. Min Range: -3.1338

Max Act: 2.6603. Min Act: -0.0000

Data Index: 324926 (C4 (Web Text))

Max Activating Token Index: 608

Text #9

Max Range: 3.1338. Min Range: -3.1338

Max Act: 2.5071. Min Act: -0.0000

Data Index: 564162 (C4 (Web Text))

Max Activating Token Index: 126

Text #10

Max Range: 3.1338. Min Range: -3.1338

Max Act: 2.4873. Min Act: -0.0000

Data Index: 370547 (C4 (Web Text))

Max Activating Token Index: 51

Text #11

Max Range: 3.1338. Min Range: -3.1338

Max Act: 2.5389. Min Act: -0.0000

Data Index: 649444 (C4 (Web Text))

Max Activating Token Index: 1014

Text #12

Max Range: 3.1338. Min Range: -3.1338

Max Act: 2.5506. Min Act: -0.0000

Data Index: 469343 (C4 (Web Text))

Max Activating Token Index: 394

Text #13

Max Range: 3.1338. Min Range: -3.1338

Max Act: 2.6579. Min Act: -0.0000

Data Index: 1133886 (C4 (Web Text))

Max Activating Token Index: 874

Text #14

Max Range: 3.1338. Min Range: -3.1338

Max Act: 2.5181. Min Act: -0.0000

Data Index: 1348448 (C4 (Web Text))

Max Activating Token Index: 379

Text #15

Max Range: 3.1338. Min Range: -3.1338

Max Act: 2.4186. Min Act: -0.0000

Data Index: 1207370 (C4 (Web Text))

Max Activating Token Index: 101

Text #16

Max Range: 3.1338. Min Range: -3.1338

Max Act: 2.5075. Min Act: -0.0000

Data Index: 1137891 (C4 (Web Text))

Max Activating Token Index: 272

Text #17

Max Range: 3.1338. Min Range: -3.1338

Max Act: 2.5042. Min Act: -0.0000

Data Index: 717970 (C4 (Web Text))

Max Activating Token Index: 64

Text #18

Max Range: 3.1338. Min Range: -3.1338

Max Act: 2.4831. Min Act: -0.0000

Data Index: 1030262 (C4 (Web Text))

Max Activating Token Index: 559

Text #19

Max Range: 3.1338. Min Range: -3.1338

Max Act: 2.3663. Min Act: -0.0000

Data Index: 1000370 (C4 (Web Text))

Max Activating Token Index: 115