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

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

Neuron 4369 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: 1.3622. Min Range: -1.3622

Max Act: 1.3276. Min Act: -0.0000

Data Index: 389692 (C4 (Web Text))

Max Activating Token Index: 529

Text #1

Max Range: 1.3622. Min Range: -1.3622

Max Act: 1.3034. Min Act: -0.0000

Data Index: 1358438 (C4 (Web Text))

Max Activating Token Index: 331

Text #2

Max Range: 1.3622. Min Range: -1.3622

Max Act: 1.2323. Min Act: -0.0000

Data Index: 1309713 (C4 (Web Text))

Max Activating Token Index: 323

Text #3

Max Range: 1.3622. Min Range: -1.3622

Max Act: 1.3186. Min Act: -0.0000

Data Index: 432380 (C4 (Web Text))

Max Activating Token Index: 119

Text #4

Max Range: 1.3622. Min Range: -1.3622

Max Act: 1.2139. Min Act: -0.0000

Data Index: 533466 (C4 (Web Text))

Max Activating Token Index: 707

Text #5

Max Range: 1.3622. Min Range: -1.3622

Max Act: 1.3622. Min Act: -0.0000

Data Index: 370609 (C4 (Web Text))

Max Activating Token Index: 357

Text #6

Max Range: 1.3622. Min Range: -1.3622

Max Act: 1.2405. Min Act: -0.0000

Data Index: 278772 (C4 (Web Text))

Max Activating Token Index: 707

Text #7

Max Range: 1.3622. Min Range: -1.3622

Max Act: 1.2124. Min Act: -0.0000

Data Index: 643374 (C4 (Web Text))

Max Activating Token Index: 666

Text #8

Max Range: 1.3622. Min Range: -1.3622

Max Act: 1.1334. Min Act: -0.0000

Data Index: 579228 (C4 (Web Text))

Max Activating Token Index: 113

Text #9

Max Range: 1.3622. Min Range: -1.3622

Max Act: 1.1563. Min Act: -0.0000

Data Index: 112373 (C4 (Web Text))

Max Activating Token Index: 706

Text #10

Max Range: 1.3622. Min Range: -1.3622

Max Act: 1.0559. Min Act: -0.0000

Data Index: 1227380 (C4 (Web Text))

Max Activating Token Index: 927

Text #11

Max Range: 1.3622. Min Range: -1.3622

Max Act: 1.0395. Min Act: -0.0000

Data Index: 780837 (C4 (Web Text))

Max Activating Token Index: 695

Text #12

Max Range: 1.3622. Min Range: -1.3622

Max Act: 1.1818. Min Act: -0.0000

Data Index: 79799 (C4 (Web Text))

Max Activating Token Index: 581

Text #13

Max Range: 1.3622. Min Range: -1.3622

Max Act: 1.1697. Min Act: -0.0000

Data Index: 414281 (C4 (Web Text))

Max Activating Token Index: 263

Text #14

Max Range: 1.3622. Min Range: -1.3622

Max Act: 1.2222. Min Act: -0.0000

Data Index: 156088 (C4 (Web Text))

Max Activating Token Index: 499

Text #15

Max Range: 1.3622. Min Range: -1.3622

Max Act: 1.1096. Min Act: -0.0000

Data Index: 1257267 (C4 (Web Text))

Max Activating Token Index: 671

Text #16

Max Range: 1.3622. Min Range: -1.3622

Max Act: 1.1034. Min Act: -0.0000

Data Index: 886589 (C4 (Web Text))

Max Activating Token Index: 617

Text #17

Max Range: 1.3622. Min Range: -1.3622

Max Act: 1.0317. Min Act: -0.0000

Data Index: 794617 (C4 (Web Text))

Max Activating Token Index: 557

Text #18

Max Range: 1.3622. Min Range: -1.3622

Max Act: 1.1073. Min Act: -0.0000

Data Index: 1036645 (C4 (Web Text))

Max Activating Token Index: 742

Text #19

Max Range: 1.3622. Min Range: -1.3622

Max Act: 1.2843. Min Act: -0.0000

Data Index: 640505 (C4 (Web Text))

Max Activating Token Index: 327