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

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

Neuron 4160 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: 1.3857. Min Range: -1.3857

Max Act: 1.3857. Min Act: -0.0000

Data Index: 1056865 (C4 (Web Text))

Max Activating Token Index: 560

Text #1

Max Range: 1.3857. Min Range: -1.3857

Max Act: 1.3027. Min Act: -0.0000

Data Index: 978975 (C4 (Web Text))

Max Activating Token Index: 667

Text #2

Max Range: 1.3857. Min Range: -1.3857

Max Act: 1.2314. Min Act: -0.0000

Data Index: 326788 (C4 (Web Text))

Max Activating Token Index: 293

Text #3

Max Range: 1.3857. Min Range: -1.3857

Max Act: 1.1434. Min Act: -0.0000

Data Index: 393386 (C4 (Web Text))

Max Activating Token Index: 199

Text #4

Max Range: 1.3857. Min Range: -1.3857

Max Act: 1.0721. Min Act: -0.0000

Data Index: 1116893 (C4 (Web Text))

Max Activating Token Index: 653

Text #5

Max Range: 1.3857. Min Range: -1.3857

Max Act: 1.1172. Min Act: -0.0000

Data Index: 740671 (C4 (Web Text))

Max Activating Token Index: 101

Text #6

Max Range: 1.3857. Min Range: -1.3857

Max Act: 1.0341. Min Act: -0.0000

Data Index: 226725 (C4 (Web Text))

Max Activating Token Index: 963

Text #7

Max Range: 1.3857. Min Range: -1.3857

Max Act: 1.1484. Min Act: -0.0000

Data Index: 219793 (C4 (Web Text))

Max Activating Token Index: 910

Text #8

Max Range: 1.3857. Min Range: -1.3857

Max Act: 0.9085. Min Act: -0.0000

Data Index: 620426 (C4 (Web Text))

Max Activating Token Index: 162

Text #9

Max Range: 1.3857. Min Range: -1.3857

Max Act: 0.9755. Min Act: -0.0000

Data Index: 679740 (C4 (Web Text))

Max Activating Token Index: 331

Text #10

Max Range: 1.3857. Min Range: -1.3857

Max Act: 1.0199. Min Act: -0.0000

Data Index: 1092081 (C4 (Web Text))

Max Activating Token Index: 453

Text #11

Max Range: 1.3857. Min Range: -1.3857

Max Act: 0.9769. Min Act: -0.0000

Data Index: 411233 (C4 (Web Text))

Max Activating Token Index: 398

Text #12

Max Range: 1.3857. Min Range: -1.3857

Max Act: 1.0293. Min Act: -0.0000

Data Index: 1100831 (C4 (Web Text))

Max Activating Token Index: 646

Text #13

Max Range: 1.3857. Min Range: -1.3857

Max Act: 0.9620. Min Act: -0.0000

Data Index: 486465 (C4 (Web Text))

Max Activating Token Index: 585

Text #14

Max Range: 1.3857. Min Range: -1.3857

Max Act: 0.9475. Min Act: -0.0000

Data Index: 631311 (C4 (Web Text))

Max Activating Token Index: 89

Text #15

Max Range: 1.3857. Min Range: -1.3857

Max Act: 0.9467. Min Act: -0.0000

Data Index: 622420 (C4 (Web Text))

Max Activating Token Index: 488

Text #16

Max Range: 1.3857. Min Range: -1.3857

Max Act: 0.9531. Min Act: -0.0000

Data Index: 550785 (C4 (Web Text))

Max Activating Token Index: 572

Text #17

Max Range: 1.3857. Min Range: -1.3857

Max Act: 0.9285. Min Act: -0.0000

Data Index: 664595 (C4 (Web Text))

Max Activating Token Index: 209

Text #18

Max Range: 1.3857. Min Range: -1.3857

Max Act: 0.7912. Min Act: -0.0000

Data Index: 442817 (C4 (Web Text))

Max Activating Token Index: 702

Text #19

Max Range: 1.3857. Min Range: -1.3857

Max Act: 0.9727. Min Act: -0.0000

Data Index: 726172 (C4 (Web Text))

Max Activating Token Index: 813