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

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

Neuron 482 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7493. Min Range: -1.7493

Max Act: 1.7493. Min Act: -0.0000

Data Index: 1068905 (C4 (Web Text))

Max Activating Token Index: 335

Text #1

Max Range: 1.7493. Min Range: -1.7493

Max Act: 1.4813. Min Act: -0.0000

Data Index: 18698 (C4 (Web Text))

Max Activating Token Index: 164

Text #2

Max Range: 1.7493. Min Range: -1.7493

Max Act: 1.5152. Min Act: -0.0000

Data Index: 612613 (C4 (Web Text))

Max Activating Token Index: 209

Text #3

Max Range: 1.7493. Min Range: -1.7493

Max Act: 1.2431. Min Act: -0.0000

Data Index: 906712 (C4 (Web Text))

Max Activating Token Index: 151

Text #4

Max Range: 1.7493. Min Range: -1.7493

Max Act: 1.3112. Min Act: -0.0000

Data Index: 1329423 (C4 (Web Text))

Max Activating Token Index: 298

Text #5

Max Range: 1.7493. Min Range: -1.7493

Max Act: 1.2946. Min Act: -0.0000

Data Index: 722433 (C4 (Web Text))

Max Activating Token Index: 903

Text #6

Max Range: 1.7493. Min Range: -1.7493

Max Act: 1.3753. Min Act: -0.0000

Data Index: 1240226 (C4 (Web Text))

Max Activating Token Index: 265

Text #7

Max Range: 1.7493. Min Range: -1.7493

Max Act: 1.2105. Min Act: -0.0000

Data Index: 322654 (C4 (Web Text))

Max Activating Token Index: 559

Text #8

Max Range: 1.7493. Min Range: -1.7493

Max Act: 1.1999. Min Act: -0.0000

Data Index: 816206 (C4 (Web Text))

Max Activating Token Index: 410

Text #9

Max Range: 1.7493. Min Range: -1.7493

Max Act: 1.1733. Min Act: -0.0000

Data Index: 47075 (C4 (Web Text))

Max Activating Token Index: 90

Text #10

Max Range: 1.7493. Min Range: -1.7493

Max Act: 1.1532. Min Act: -0.0000

Data Index: 404893 (C4 (Web Text))

Max Activating Token Index: 292

Text #11

Max Range: 1.7493. Min Range: -1.7493

Max Act: 1.1450. Min Act: -0.0000

Data Index: 248998 (C4 (Web Text))

Max Activating Token Index: 434

Text #12

Max Range: 1.7493. Min Range: -1.7493

Max Act: 1.0661. Min Act: -0.0000

Data Index: 1116720 (C4 (Web Text))

Max Activating Token Index: 272

Text #13

Max Range: 1.7493. Min Range: -1.7493

Max Act: 0.9734. Min Act: -0.0000

Data Index: 602105 (C4 (Web Text))

Max Activating Token Index: 73

Text #14

Max Range: 1.7493. Min Range: -1.7493

Max Act: 0.9493. Min Act: -0.0000

Data Index: 450822 (C4 (Web Text))

Max Activating Token Index: 384

Text #15

Max Range: 1.7493. Min Range: -1.7493

Max Act: 0.9780. Min Act: -0.0000

Data Index: 171037 (C4 (Web Text))

Max Activating Token Index: 844

Text #16

Max Range: 1.7493. Min Range: -1.7493

Max Act: 0.9235. Min Act: -0.0000

Data Index: 695435 (C4 (Web Text))

Max Activating Token Index: 655

Text #17

Max Range: 1.7493. Min Range: -1.7493

Max Act: 0.8815. Min Act: -0.0000

Data Index: 1016280 (C4 (Web Text))

Max Activating Token Index: 80

Text #18

Max Range: 1.7493. Min Range: -1.7493

Max Act: 0.9214. Min Act: -0.0000

Data Index: 1347223 (C4 (Web Text))

Max Activating Token Index: 717

Text #19

Max Range: 1.7493. Min Range: -1.7493

Max Act: 0.8688. Min Act: -0.0000

Data Index: 425904 (C4 (Web Text))

Max Activating Token Index: 930