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

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

Neuron 368 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3864. Min Range: -1.3864

Max Act: 1.3864. Min Act: -0.0000

Data Index: 729916 (C4 (Web Text))

Max Activating Token Index: 959

Text #1

Max Range: 1.3864. Min Range: -1.3864

Max Act: 1.2645. Min Act: -0.0000

Data Index: 1345688 (C4 (Web Text))

Max Activating Token Index: 156

Text #2

Max Range: 1.3864. Min Range: -1.3864

Max Act: 1.1989. Min Act: -0.0000

Data Index: 195861 (C4 (Web Text))

Max Activating Token Index: 349

Text #3

Max Range: 1.3864. Min Range: -1.3864

Max Act: 1.1984. Min Act: -0.0000

Data Index: 1040760 (C4 (Web Text))

Max Activating Token Index: 193

Text #4

Max Range: 1.3864. Min Range: -1.3864

Max Act: 1.1891. Min Act: -0.0000

Data Index: 1147966 (C4 (Web Text))

Max Activating Token Index: 619

Text #5

Max Range: 1.3864. Min Range: -1.3864

Max Act: 1.1462. Min Act: -0.0000

Data Index: 596985 (C4 (Web Text))

Max Activating Token Index: 106

Text #6

Max Range: 1.3864. Min Range: -1.3864

Max Act: 1.1529. Min Act: -0.0000

Data Index: 647350 (C4 (Web Text))

Max Activating Token Index: 237

Text #7

Max Range: 1.3864. Min Range: -1.3864

Max Act: 1.1126. Min Act: -0.0000

Data Index: 1055492 (C4 (Web Text))

Max Activating Token Index: 806

Text #8

Max Range: 1.3864. Min Range: -1.3864

Max Act: 1.0785. Min Act: -0.0000

Data Index: 692861 (C4 (Web Text))

Max Activating Token Index: 174

Text #9

Max Range: 1.3864. Min Range: -1.3864

Max Act: 1.1133. Min Act: -0.0000

Data Index: 185328 (C4 (Web Text))

Max Activating Token Index: 457

Text #10

Max Range: 1.3864. Min Range: -1.3864

Max Act: 1.0589. Min Act: -0.0000

Data Index: 890167 (C4 (Web Text))

Max Activating Token Index: 514

Text #11

Max Range: 1.3864. Min Range: -1.3864

Max Act: 0.9409. Min Act: -0.0000

Data Index: 493135 (C4 (Web Text))

Max Activating Token Index: 689

Text #12

Max Range: 1.3864. Min Range: -1.3864

Max Act: 1.0501. Min Act: -0.0000

Data Index: 713607 (C4 (Web Text))

Max Activating Token Index: 302

Text #13

Max Range: 1.3864. Min Range: -1.3864

Max Act: 0.9995. Min Act: -0.0000

Data Index: 1184043 (C4 (Web Text))

Max Activating Token Index: 403

Text #14

Max Range: 1.3864. Min Range: -1.3864

Max Act: 1.1273. Min Act: -0.0000

Data Index: 688866 (C4 (Web Text))

Max Activating Token Index: 659

Text #15

Max Range: 1.3864. Min Range: -1.3864

Max Act: 1.0176. Min Act: -0.0000

Data Index: 1039966 (C4 (Web Text))

Max Activating Token Index: 54

Text #16

Max Range: 1.3864. Min Range: -1.3864

Max Act: 0.9445. Min Act: -0.0000

Data Index: 1356366 (C4 (Web Text))

Max Activating Token Index: 156

Text #17

Max Range: 1.3864. Min Range: -1.3864

Max Act: 1.0140. Min Act: -0.0000

Data Index: 10630 (C4 (Web Text))

Max Activating Token Index: 232

Text #18

Max Range: 1.3864. Min Range: -1.3864

Max Act: 0.9743. Min Act: -0.0000

Data Index: 430392 (C4 (Web Text))

Max Activating Token Index: 245

Text #19

Max Range: 1.3864. Min Range: -1.3864

Max Act: 0.9779. Min Act: -0.0000

Data Index: 220011 (C4 (Web Text))

Max Activating Token Index: 878