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

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

Neuron 2492 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.8527. Min Act: -0.0000

Data Index: 129596 (C4 (Web Text))

Max Activating Token Index: 857

Text #1

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.7861. Min Act: -0.0000

Data Index: 316022 (C4 (Web Text))

Max Activating Token Index: 763

Text #2

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.7211. Min Act: -0.0000

Data Index: 524505 (C4 (Web Text))

Max Activating Token Index: 988

Text #3

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.7058. Min Act: -0.0000

Data Index: 478974 (C4 (Web Text))

Max Activating Token Index: 1005

Text #4

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.6759. Min Act: -0.0000

Data Index: 458901 (C4 (Web Text))

Max Activating Token Index: 188

Text #5

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.6487. Min Act: -0.0000

Data Index: 822221 (C4 (Web Text))

Max Activating Token Index: 986

Text #6

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.6266. Min Act: -0.0000

Data Index: 1279417 (C4 (Web Text))

Max Activating Token Index: 232

Text #7

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.6143. Min Act: -0.0000

Data Index: 607836 (C4 (Web Text))

Max Activating Token Index: 369

Text #8

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.6291. Min Act: -0.0000

Data Index: 1587158 (Python Code)

Max Activating Token Index: 298

Text #9

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.5814. Min Act: -0.0000

Data Index: 1031905 (C4 (Web Text))

Max Activating Token Index: 907

Text #10

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.5789. Min Act: -0.0000

Data Index: 1609141 (Python Code)

Max Activating Token Index: 96

Text #11

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.5730. Min Act: -0.0000

Data Index: 1028924 (C4 (Web Text))

Max Activating Token Index: 596

Text #12

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.5692. Min Act: -0.0000

Data Index: 15699 (C4 (Web Text))

Max Activating Token Index: 244

Text #13

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.5580. Min Act: -0.0000

Data Index: 651815 (C4 (Web Text))

Max Activating Token Index: 496

Text #14

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.5578. Min Act: -0.0000

Data Index: 855433 (C4 (Web Text))

Max Activating Token Index: 418

Text #15

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.5764. Min Act: -0.0000

Data Index: 874890 (C4 (Web Text))

Max Activating Token Index: 517

Text #16

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.5501. Min Act: -0.0000

Data Index: 356490 (C4 (Web Text))

Max Activating Token Index: 469

Text #17

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.5802. Min Act: -0.0000

Data Index: 300460 (C4 (Web Text))

Max Activating Token Index: 507

Text #18

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.5241. Min Act: -0.0000

Data Index: 385817 (C4 (Web Text))

Max Activating Token Index: 248

Text #19

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.5327. Min Act: -0.0000

Data Index: 904828 (C4 (Web Text))

Max Activating Token Index: 937