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

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

Neuron 5000 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3587. Min Range: -1.3587

Max Act: 1.3587. Min Act: -0.0000

Data Index: 237156 (C4 (Web Text))

Max Activating Token Index: 372

Text #1

Max Range: 1.3587. Min Range: -1.3587

Max Act: 1.3205. Min Act: -0.0000

Data Index: 921979 (C4 (Web Text))

Max Activating Token Index: 320

Text #2

Max Range: 1.3587. Min Range: -1.3587

Max Act: 1.3045. Min Act: -0.0000

Data Index: 179423 (C4 (Web Text))

Max Activating Token Index: 126

Text #3

Max Range: 1.3587. Min Range: -1.3587

Max Act: 1.1182. Min Act: -0.0000

Data Index: 237060 (C4 (Web Text))

Max Activating Token Index: 207

Text #4

Max Range: 1.3587. Min Range: -1.3587

Max Act: 1.1749. Min Act: -0.0000

Data Index: 1014808 (C4 (Web Text))

Max Activating Token Index: 396

Text #5

Max Range: 1.3587. Min Range: -1.3587

Max Act: 1.3016. Min Act: -0.0000

Data Index: 277403 (C4 (Web Text))

Max Activating Token Index: 504

Text #6

Max Range: 1.3587. Min Range: -1.3587

Max Act: 1.1805. Min Act: -0.0000

Data Index: 420845 (C4 (Web Text))

Max Activating Token Index: 451

Text #7

Max Range: 1.3587. Min Range: -1.3587

Max Act: 1.1633. Min Act: -0.0000

Data Index: 672331 (C4 (Web Text))

Max Activating Token Index: 930

Text #8

Max Range: 1.3587. Min Range: -1.3587

Max Act: 1.1705. Min Act: -0.0000

Data Index: 114743 (C4 (Web Text))

Max Activating Token Index: 872

Text #9

Max Range: 1.3587. Min Range: -1.3587

Max Act: 1.1598. Min Act: -0.0000

Data Index: 1071910 (C4 (Web Text))

Max Activating Token Index: 144

Text #10

Max Range: 1.3587. Min Range: -1.3587

Max Act: 1.1643. Min Act: -0.0000

Data Index: 399677 (C4 (Web Text))

Max Activating Token Index: 340

Text #11

Max Range: 1.3587. Min Range: -1.3587

Max Act: 1.1653. Min Act: -0.0000

Data Index: 1303679 (C4 (Web Text))

Max Activating Token Index: 77

Text #12

Max Range: 1.3587. Min Range: -1.3587

Max Act: 1.1623. Min Act: -0.0000

Data Index: 1359772 (C4 (Web Text))

Max Activating Token Index: 603

Text #13

Max Range: 1.3587. Min Range: -1.3587

Max Act: 1.1267. Min Act: -0.0000

Data Index: 142820 (C4 (Web Text))

Max Activating Token Index: 560

Text #14

Max Range: 1.3587. Min Range: -1.3587

Max Act: 1.1144. Min Act: -0.0000

Data Index: 304315 (C4 (Web Text))

Max Activating Token Index: 33

Text #15

Max Range: 1.3587. Min Range: -1.3587

Max Act: 1.0965. Min Act: -0.0000

Data Index: 964144 (C4 (Web Text))

Max Activating Token Index: 215

Text #16

Max Range: 1.3587. Min Range: -1.3587

Max Act: 1.1706. Min Act: -0.0000

Data Index: 181041 (C4 (Web Text))

Max Activating Token Index: 449

Text #17

Max Range: 1.3587. Min Range: -1.3587

Max Act: 1.1309. Min Act: -0.0000

Data Index: 110077 (C4 (Web Text))

Max Activating Token Index: 916

Text #18

Max Range: 1.3587. Min Range: -1.3587

Max Act: 1.0917. Min Act: -0.0000

Data Index: 211953 (C4 (Web Text))

Max Activating Token Index: 638

Text #19

Max Range: 1.3587. Min Range: -1.3587

Max Act: 1.0901. Min Act: -0.0000

Data Index: 272935 (C4 (Web Text))

Max Activating Token Index: 697