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

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

Neuron 3000 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: 1.7663. Min Range: -1.7663

Max Act: 1.7663. Min Act: -0.0000

Data Index: 371557 (C4 (Web Text))

Max Activating Token Index: 254

Text #1

Max Range: 1.7663. Min Range: -1.7663

Max Act: 1.4620. Min Act: -0.0000

Data Index: 743651 (C4 (Web Text))

Max Activating Token Index: 614

Text #2

Max Range: 1.7663. Min Range: -1.7663

Max Act: 1.4156. Min Act: -0.0000

Data Index: 686048 (C4 (Web Text))

Max Activating Token Index: 479

Text #3

Max Range: 1.7663. Min Range: -1.7663

Max Act: 1.3066. Min Act: -0.0000

Data Index: 546143 (C4 (Web Text))

Max Activating Token Index: 157

Text #4

Max Range: 1.7663. Min Range: -1.7663

Max Act: 1.3094. Min Act: -0.0000

Data Index: 1297889 (C4 (Web Text))

Max Activating Token Index: 633

Text #5

Max Range: 1.7663. Min Range: -1.7663

Max Act: 1.3350. Min Act: -0.0000

Data Index: 538230 (C4 (Web Text))

Max Activating Token Index: 985

Text #6

Max Range: 1.7663. Min Range: -1.7663

Max Act: 1.3301. Min Act: -0.0000

Data Index: 1270821 (C4 (Web Text))

Max Activating Token Index: 496

Text #7

Max Range: 1.7663. Min Range: -1.7663

Max Act: 1.3655. Min Act: -0.0000

Data Index: 672635 (C4 (Web Text))

Max Activating Token Index: 109

Text #8

Max Range: 1.7663. Min Range: -1.7663

Max Act: 1.2736. Min Act: -0.0000

Data Index: 1245281 (C4 (Web Text))

Max Activating Token Index: 121

Text #9

Max Range: 1.7663. Min Range: -1.7663

Max Act: 1.2358. Min Act: -0.0000

Data Index: 774865 (C4 (Web Text))

Max Activating Token Index: 840

Text #10

Max Range: 1.7663. Min Range: -1.7663

Max Act: 1.1977. Min Act: -0.0000

Data Index: 42695 (C4 (Web Text))

Max Activating Token Index: 715

Text #11

Max Range: 1.7663. Min Range: -1.7663

Max Act: 1.1609. Min Act: -0.0000

Data Index: 643663 (C4 (Web Text))

Max Activating Token Index: 885

Text #12

Max Range: 1.7663. Min Range: -1.7663

Max Act: 1.0976. Min Act: -0.0000

Data Index: 804240 (C4 (Web Text))

Max Activating Token Index: 829

Text #13

Max Range: 1.7663. Min Range: -1.7663

Max Act: 1.1191. Min Act: -0.0000

Data Index: 161034 (C4 (Web Text))

Max Activating Token Index: 509

Text #14

Max Range: 1.7663. Min Range: -1.7663

Max Act: 1.0881. Min Act: -0.0000

Data Index: 935076 (C4 (Web Text))

Max Activating Token Index: 689

Text #15

Max Range: 1.7663. Min Range: -1.7663

Max Act: 1.1033. Min Act: -0.0000

Data Index: 1192228 (C4 (Web Text))

Max Activating Token Index: 352

Text #16

Max Range: 1.7663. Min Range: -1.7663

Max Act: 1.1042. Min Act: -0.0000

Data Index: 1175311 (C4 (Web Text))

Max Activating Token Index: 102

Text #17

Max Range: 1.7663. Min Range: -1.7663

Max Act: 1.1170. Min Act: -0.0000

Data Index: 345172 (C4 (Web Text))

Max Activating Token Index: 284

Text #18

Max Range: 1.7663. Min Range: -1.7663

Max Act: 1.1272. Min Act: -0.0000

Data Index: 210391 (C4 (Web Text))

Max Activating Token Index: 746

Text #19

Max Range: 1.7663. Min Range: -1.7663

Max Act: 1.0516. Min Act: -0.0000

Data Index: 291301 (C4 (Web Text))

Max Activating Token Index: 579