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

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

Neuron 3941 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6643. Min Range: -3.6643

Max Act: 3.6643. Min Act: -0.0000

Data Index: 95019 (C4 (Web Text))

Max Activating Token Index: 880

Text #1

Max Range: 3.6643. Min Range: -3.6643

Max Act: 3.5923. Min Act: -0.0000

Data Index: 403654 (C4 (Web Text))

Max Activating Token Index: 907

Text #2

Max Range: 3.6643. Min Range: -3.6643

Max Act: 3.4766. Min Act: -0.0000

Data Index: 1264884 (C4 (Web Text))

Max Activating Token Index: 997

Text #3

Max Range: 3.6643. Min Range: -3.6643

Max Act: 3.1623. Min Act: -0.0000

Data Index: 223033 (C4 (Web Text))

Max Activating Token Index: 519

Text #4

Max Range: 3.6643. Min Range: -3.6643

Max Act: 3.2390. Min Act: -0.0000

Data Index: 615859 (C4 (Web Text))

Max Activating Token Index: 422

Text #5

Max Range: 3.6643. Min Range: -3.6643

Max Act: 3.0747. Min Act: -0.0000

Data Index: 8591 (C4 (Web Text))

Max Activating Token Index: 820

Text #6

Max Range: 3.6643. Min Range: -3.6643

Max Act: 2.8897. Min Act: -0.0000

Data Index: 344438 (C4 (Web Text))

Max Activating Token Index: 387

Text #7

Max Range: 3.6643. Min Range: -3.6643

Max Act: 2.9443. Min Act: -0.0000

Data Index: 579940 (C4 (Web Text))

Max Activating Token Index: 287

Text #8

Max Range: 3.6643. Min Range: -3.6643

Max Act: 2.9380. Min Act: -0.0000

Data Index: 815774 (C4 (Web Text))

Max Activating Token Index: 491

Text #9

Max Range: 3.6643. Min Range: -3.6643

Max Act: 2.9309. Min Act: -0.0000

Data Index: 1345073 (C4 (Web Text))

Max Activating Token Index: 817

Text #10

Max Range: 3.6643. Min Range: -3.6643

Max Act: 2.9191. Min Act: -0.0000

Data Index: 273755 (C4 (Web Text))

Max Activating Token Index: 782

Text #11

Max Range: 3.6643. Min Range: -3.6643

Max Act: 2.7657. Min Act: -0.0000

Data Index: 361090 (C4 (Web Text))

Max Activating Token Index: 721

Text #12

Max Range: 3.6643. Min Range: -3.6643

Max Act: 2.7584. Min Act: -0.0000

Data Index: 535155 (C4 (Web Text))

Max Activating Token Index: 864

Text #13

Max Range: 3.6643. Min Range: -3.6643

Max Act: 2.8827. Min Act: -0.0000

Data Index: 533148 (C4 (Web Text))

Max Activating Token Index: 535

Text #14

Max Range: 3.6643. Min Range: -3.6643

Max Act: 2.8527. Min Act: -0.0000

Data Index: 838330 (C4 (Web Text))

Max Activating Token Index: 447

Text #15

Max Range: 3.6643. Min Range: -3.6643

Max Act: 2.8670. Min Act: -0.0000

Data Index: 244025 (C4 (Web Text))

Max Activating Token Index: 812

Text #16

Max Range: 3.6643. Min Range: -3.6643

Max Act: 2.8634. Min Act: -0.0000

Data Index: 1099417 (C4 (Web Text))

Max Activating Token Index: 1003

Text #17

Max Range: 3.6643. Min Range: -3.6643

Max Act: 2.7238. Min Act: -0.0000

Data Index: 1260953 (C4 (Web Text))

Max Activating Token Index: 194

Text #18

Max Range: 3.6643. Min Range: -3.6643

Max Act: 2.8287. Min Act: -0.0000

Data Index: 23120 (C4 (Web Text))

Max Activating Token Index: 561

Text #19

Max Range: 3.6643. Min Range: -3.6643

Max Act: 2.8269. Min Act: -0.0000

Data Index: 619226 (C4 (Web Text))

Max Activating Token Index: 873