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

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

Neuron 5392 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2191. Min Range: -1.2191

Max Act: 1.2191. Min Act: -0.0001

Data Index: 959134 (C4 (Web Text))

Max Activating Token Index: 27

Text #1

Max Range: 1.2191. Min Range: -1.2191

Max Act: 1.0136. Min Act: -0.0000

Data Index: 1054343 (C4 (Web Text))

Max Activating Token Index: 28

Text #2

Max Range: 1.2191. Min Range: -1.2191

Max Act: 1.0708. Min Act: -0.0001

Data Index: 1198633 (C4 (Web Text))

Max Activating Token Index: 294

Text #3

Max Range: 1.2191. Min Range: -1.2191

Max Act: 1.0239. Min Act: -0.0000

Data Index: 714730 (C4 (Web Text))

Max Activating Token Index: 454

Text #4

Max Range: 1.2191. Min Range: -1.2191

Max Act: 1.1488. Min Act: -0.0000

Data Index: 368202 (C4 (Web Text))

Max Activating Token Index: 794

Text #5

Max Range: 1.2191. Min Range: -1.2191

Max Act: 0.9404. Min Act: -0.0000

Data Index: 256573 (C4 (Web Text))

Max Activating Token Index: 831

Text #6

Max Range: 1.2191. Min Range: -1.2191

Max Act: 0.9745. Min Act: -0.0000

Data Index: 1062454 (C4 (Web Text))

Max Activating Token Index: 47

Text #7

Max Range: 1.2191. Min Range: -1.2191

Max Act: 0.9049. Min Act: -0.0000

Data Index: 925530 (C4 (Web Text))

Max Activating Token Index: 249

Text #8

Max Range: 1.2191. Min Range: -1.2191

Max Act: 0.9100. Min Act: -0.0001

Data Index: 560682 (C4 (Web Text))

Max Activating Token Index: 755

Text #9

Max Range: 1.2191. Min Range: -1.2191

Max Act: 0.9253. Min Act: -0.0000

Data Index: 981424 (C4 (Web Text))

Max Activating Token Index: 419

Text #10

Max Range: 1.2191. Min Range: -1.2191

Max Act: 0.8558. Min Act: -0.0000

Data Index: 306168 (C4 (Web Text))

Max Activating Token Index: 580

Text #11

Max Range: 1.2191. Min Range: -1.2191

Max Act: 0.8757. Min Act: -0.0000

Data Index: 1279046 (C4 (Web Text))

Max Activating Token Index: 908

Text #12

Max Range: 1.2191. Min Range: -1.2191

Max Act: 0.8754. Min Act: -0.0001

Data Index: 991755 (C4 (Web Text))

Max Activating Token Index: 448

Text #13

Max Range: 1.2191. Min Range: -1.2191

Max Act: 0.8715. Min Act: -0.0000

Data Index: 719821 (C4 (Web Text))

Max Activating Token Index: 637

Text #14

Max Range: 1.2191. Min Range: -1.2191

Max Act: 0.7937. Min Act: -0.0000

Data Index: 685896 (C4 (Web Text))

Max Activating Token Index: 768

Text #15

Max Range: 1.2191. Min Range: -1.2191

Max Act: 0.8216. Min Act: -0.0000

Data Index: 77039 (C4 (Web Text))

Max Activating Token Index: 7

Text #16

Max Range: 1.2191. Min Range: -1.2191

Max Act: 0.8050. Min Act: -0.0001

Data Index: 744086 (C4 (Web Text))

Max Activating Token Index: 314

Text #17

Max Range: 1.2191. Min Range: -1.2191

Max Act: 0.7686. Min Act: -0.0001

Data Index: 953083 (C4 (Web Text))

Max Activating Token Index: 339

Text #18

Max Range: 1.2191. Min Range: -1.2191

Max Act: 0.7967. Min Act: -0.0000

Data Index: 932615 (C4 (Web Text))

Max Activating Token Index: 1022

Text #19

Max Range: 1.2191. Min Range: -1.2191

Max Act: 0.8652. Min Act: -0.0000

Data Index: 736848 (C4 (Web Text))

Max Activating Token Index: 623