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

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

Neuron 1917 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: 1.0636. Min Range: -1.0636

Max Act: 1.0636. Min Act: -0.0000

Data Index: 1352012 (C4 (Web Text))

Max Activating Token Index: 963

Text #1

Max Range: 1.0636. Min Range: -1.0636

Max Act: 0.9954. Min Act: -0.0000

Data Index: 361202 (C4 (Web Text))

Max Activating Token Index: 36

Text #2

Max Range: 1.0636. Min Range: -1.0636

Max Act: 0.9191. Min Act: -0.0000

Data Index: 516576 (C4 (Web Text))

Max Activating Token Index: 489

Text #3

Max Range: 1.0636. Min Range: -1.0636

Max Act: 0.9091. Min Act: -0.0000

Data Index: 1013424 (C4 (Web Text))

Max Activating Token Index: 376

Text #4

Max Range: 1.0636. Min Range: -1.0636

Max Act: 0.8871. Min Act: -0.0000

Data Index: 1196485 (C4 (Web Text))

Max Activating Token Index: 14

Text #5

Max Range: 1.0636. Min Range: -1.0636

Max Act: 0.8432. Min Act: -0.0000

Data Index: 878334 (C4 (Web Text))

Max Activating Token Index: 771

Text #6

Max Range: 1.0636. Min Range: -1.0636

Max Act: 0.9182. Min Act: -0.0000

Data Index: 629679 (C4 (Web Text))

Max Activating Token Index: 570

Text #7

Max Range: 1.0636. Min Range: -1.0636

Max Act: 0.8518. Min Act: -0.0000

Data Index: 59948 (C4 (Web Text))

Max Activating Token Index: 983

Text #8

Max Range: 1.0636. Min Range: -1.0636

Max Act: 0.8243. Min Act: -0.0000

Data Index: 1332621 (C4 (Web Text))

Max Activating Token Index: 34

Text #9

Max Range: 1.0636. Min Range: -1.0636

Max Act: 0.8259. Min Act: -0.0000

Data Index: 135591 (C4 (Web Text))

Max Activating Token Index: 413

Text #10

Max Range: 1.0636. Min Range: -1.0636

Max Act: 0.7642. Min Act: -0.0000

Data Index: 1177534 (C4 (Web Text))

Max Activating Token Index: 861

Text #11

Max Range: 1.0636. Min Range: -1.0636

Max Act: 0.7947. Min Act: -0.0000

Data Index: 752974 (C4 (Web Text))

Max Activating Token Index: 163

Text #12

Max Range: 1.0636. Min Range: -1.0636

Max Act: 0.7769. Min Act: 0.0000

Data Index: 163818 (C4 (Web Text))

Max Activating Token Index: 410

Text #13

Max Range: 1.0636. Min Range: -1.0636

Max Act: 0.7322. Min Act: -0.0000

Data Index: 688964 (C4 (Web Text))

Max Activating Token Index: 199

Text #14

Max Range: 1.0636. Min Range: -1.0636

Max Act: 0.7375. Min Act: -0.0000

Data Index: 86494 (C4 (Web Text))

Max Activating Token Index: 669

Text #15

Max Range: 1.0636. Min Range: -1.0636

Max Act: 0.7427. Min Act: -0.0000

Data Index: 1334578 (C4 (Web Text))

Max Activating Token Index: 818

Text #16

Max Range: 1.0636. Min Range: -1.0636

Max Act: 0.7432. Min Act: -0.0000

Data Index: 641464 (C4 (Web Text))

Max Activating Token Index: 531

Text #17

Max Range: 1.0636. Min Range: -1.0636

Max Act: 0.7655. Min Act: 0.0001

Data Index: 446533 (C4 (Web Text))

Max Activating Token Index: 890

Text #18

Max Range: 1.0636. Min Range: -1.0636

Max Act: 0.7160. Min Act: -0.0000

Data Index: 366281 (C4 (Web Text))

Max Activating Token Index: 533

Text #19

Max Range: 1.0636. Min Range: -1.0636

Max Act: 0.6669. Min Act: -0.0000

Data Index: 461769 (C4 (Web Text))

Max Activating Token Index: 639