Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 637 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2857. Min Range: -0.2857

Max Act: 0.2707. Min Act: -0.0001

Data Index: 1269256 (C4 (Web Text))

Max Activating Token Index: 949

Text #1

Max Range: 0.2857. Min Range: -0.2857

Max Act: 0.2685. Min Act: -0.0001

Data Index: 1070814 (C4 (Web Text))

Max Activating Token Index: 953

Text #2

Max Range: 0.2857. Min Range: -0.2857

Max Act: 0.2463. Min Act: -0.0001

Data Index: 189312 (C4 (Web Text))

Max Activating Token Index: 773

Text #3

Max Range: 0.2857. Min Range: -0.2857

Max Act: 0.2857. Min Act: -0.0001

Data Index: 1064953 (C4 (Web Text))

Max Activating Token Index: 649

Text #4

Max Range: 0.2857. Min Range: -0.2857

Max Act: 0.2645. Min Act: -0.0001

Data Index: 595899 (C4 (Web Text))

Max Activating Token Index: 686

Text #5

Max Range: 0.2857. Min Range: -0.2857

Max Act: 0.2463. Min Act: -0.0001

Data Index: 91258 (C4 (Web Text))

Max Activating Token Index: 859

Text #6

Max Range: 0.2857. Min Range: -0.2857

Max Act: 0.2404. Min Act: -0.0001

Data Index: 373572 (C4 (Web Text))

Max Activating Token Index: 722

Text #7

Max Range: 0.2857. Min Range: -0.2857

Max Act: 0.2627. Min Act: -0.0001

Data Index: 500284 (C4 (Web Text))

Max Activating Token Index: 856

Text #8

Max Range: 0.2857. Min Range: -0.2857

Max Act: 0.2337. Min Act: -0.0001

Data Index: 610242 (C4 (Web Text))

Max Activating Token Index: 941

Text #9

Max Range: 0.2857. Min Range: -0.2857

Max Act: 0.2409. Min Act: -0.0001

Data Index: 260446 (C4 (Web Text))

Max Activating Token Index: 777

Text #10

Max Range: 0.2857. Min Range: -0.2857

Max Act: 0.2573. Min Act: -0.0001

Data Index: 960248 (C4 (Web Text))

Max Activating Token Index: 615

Text #11

Max Range: 0.2857. Min Range: -0.2857

Max Act: 0.2087. Min Act: -0.0001

Data Index: 604593 (C4 (Web Text))

Max Activating Token Index: 696

Text #12

Max Range: 0.2857. Min Range: -0.2857

Max Act: 0.2556. Min Act: -0.0001

Data Index: 1113004 (C4 (Web Text))

Max Activating Token Index: 812

Text #13

Max Range: 0.2857. Min Range: -0.2857

Max Act: 0.2170. Min Act: -0.0001

Data Index: 1193212 (C4 (Web Text))

Max Activating Token Index: 646

Text #14

Max Range: 0.2857. Min Range: -0.2857

Max Act: 0.2304. Min Act: -0.0001

Data Index: 961469 (C4 (Web Text))

Max Activating Token Index: 641

Text #15

Max Range: 0.2857. Min Range: -0.2857

Max Act: 0.2304. Min Act: -0.0001

Data Index: 746129 (C4 (Web Text))

Max Activating Token Index: 739

Text #16

Max Range: 0.2857. Min Range: -0.2857

Max Act: 0.2438. Min Act: -0.0001

Data Index: 315152 (C4 (Web Text))

Max Activating Token Index: 537

Text #17

Max Range: 0.2857. Min Range: -0.2857

Max Act: 0.2245. Min Act: -0.0001

Data Index: 126051 (C4 (Web Text))

Max Activating Token Index: 826

Text #18

Max Range: 0.2857. Min Range: -0.2857

Max Act: 0.2170. Min Act: -0.0001

Data Index: 1238324 (C4 (Web Text))

Max Activating Token Index: 382

Text #19

Max Range: 0.2857. Min Range: -0.2857

Max Act: 0.2226. Min Act: -0.0001

Data Index: 70562 (C4 (Web Text))

Max Activating Token Index: 602