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

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

Neuron 4583 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2250. Min Range: -0.2250

Max Act: 0.2218. Min Act: -0.0000

Data Index: 594265 (C4 (Web Text))

Max Activating Token Index: 725

Text #1

Max Range: 0.2250. Min Range: -0.2250

Max Act: 0.2250. Min Act: -0.0000

Data Index: 685497 (C4 (Web Text))

Max Activating Token Index: 549

Text #2

Max Range: 0.2250. Min Range: -0.2250

Max Act: 0.2237. Min Act: -0.0000

Data Index: 99087 (C4 (Web Text))

Max Activating Token Index: 897

Text #3

Max Range: 0.2250. Min Range: -0.2250

Max Act: 0.2097. Min Act: -0.0000

Data Index: 1190101 (C4 (Web Text))

Max Activating Token Index: 971

Text #4

Max Range: 0.2250. Min Range: -0.2250

Max Act: 0.2059. Min Act: -0.0000

Data Index: 431797 (C4 (Web Text))

Max Activating Token Index: 910

Text #5

Max Range: 0.2250. Min Range: -0.2250

Max Act: 0.1998. Min Act: -0.0000

Data Index: 35158 (C4 (Web Text))

Max Activating Token Index: 506

Text #6

Max Range: 0.2250. Min Range: -0.2250

Max Act: 0.1685. Min Act: -0.0000

Data Index: 1358416 (C4 (Web Text))

Max Activating Token Index: 755

Text #7

Max Range: 0.2250. Min Range: -0.2250

Max Act: 0.1768. Min Act: -0.0000

Data Index: 369416 (C4 (Web Text))

Max Activating Token Index: 690

Text #8

Max Range: 0.2250. Min Range: -0.2250

Max Act: 0.1829. Min Act: -0.0000

Data Index: 40455 (C4 (Web Text))

Max Activating Token Index: 88

Text #9

Max Range: 0.2250. Min Range: -0.2250

Max Act: 0.1956. Min Act: -0.0000

Data Index: 59016 (C4 (Web Text))

Max Activating Token Index: 499

Text #10

Max Range: 0.2250. Min Range: -0.2250

Max Act: 0.1794. Min Act: -0.0000

Data Index: 92270 (C4 (Web Text))

Max Activating Token Index: 106

Text #11

Max Range: 0.2250. Min Range: -0.2250

Max Act: 0.1688. Min Act: -0.0000

Data Index: 255393 (C4 (Web Text))

Max Activating Token Index: 574

Text #12

Max Range: 0.2250. Min Range: -0.2250

Max Act: 0.1799. Min Act: -0.0000

Data Index: 889401 (C4 (Web Text))

Max Activating Token Index: 538

Text #13

Max Range: 0.2250. Min Range: -0.2250

Max Act: 0.1723. Min Act: -0.0000

Data Index: 1089496 (C4 (Web Text))

Max Activating Token Index: 387

Text #14

Max Range: 0.2250. Min Range: -0.2250

Max Act: 0.1705. Min Act: -0.0000

Data Index: 1275703 (C4 (Web Text))

Max Activating Token Index: 42

Text #15

Max Range: 0.2250. Min Range: -0.2250

Max Act: 0.1788. Min Act: -0.0000

Data Index: 118976 (C4 (Web Text))

Max Activating Token Index: 335

Text #16

Max Range: 0.2250. Min Range: -0.2250

Max Act: 0.1695. Min Act: -0.0000

Data Index: 1080815 (C4 (Web Text))

Max Activating Token Index: 386

Text #17

Max Range: 0.2250. Min Range: -0.2250

Max Act: 0.1742. Min Act: -0.0000

Data Index: 43700 (C4 (Web Text))

Max Activating Token Index: 83

Text #18

Max Range: 0.2250. Min Range: -0.2250

Max Act: 0.1682. Min Act: -0.0000

Data Index: 758998 (C4 (Web Text))

Max Activating Token Index: 261

Text #19

Max Range: 0.2250. Min Range: -0.2250

Max Act: 0.1641. Min Act: -0.0000

Data Index: 124202 (C4 (Web Text))

Max Activating Token Index: 454