Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1353 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.2557. Min Range: -1.2557

Max Act: 1.2105. Min Act: -0.0001

Data Index: 119191 (C4 (Web Text))

Max Activating Token Index: 781

Text #1

Max Range: 1.2557. Min Range: -1.2557

Max Act: 1.1592. Min Act: -0.0001

Data Index: 811427 (C4 (Web Text))

Max Activating Token Index: 184

Text #2

Max Range: 1.2557. Min Range: -1.2557

Max Act: 1.2557. Min Act: -0.0001

Data Index: 248238 (C4 (Web Text))

Max Activating Token Index: 811

Text #3

Max Range: 1.2557. Min Range: -1.2557

Max Act: 1.0736. Min Act: -0.0001

Data Index: 647400 (C4 (Web Text))

Max Activating Token Index: 818

Text #4

Max Range: 1.2557. Min Range: -1.2557

Max Act: 1.1562. Min Act: -0.0001

Data Index: 506336 (C4 (Web Text))

Max Activating Token Index: 867

Text #5

Max Range: 1.2557. Min Range: -1.2557

Max Act: 1.1502. Min Act: -0.0001

Data Index: 1195321 (C4 (Web Text))

Max Activating Token Index: 468

Text #6

Max Range: 1.2557. Min Range: -1.2557

Max Act: 1.1097. Min Act: -0.0001

Data Index: 1241798 (C4 (Web Text))

Max Activating Token Index: 476

Text #7

Max Range: 1.2557. Min Range: -1.2557

Max Act: 1.0786. Min Act: -0.0001

Data Index: 1222020 (C4 (Web Text))

Max Activating Token Index: 632

Text #8

Max Range: 1.2557. Min Range: -1.2557

Max Act: 0.9944. Min Act: -0.0001

Data Index: 1313370 (C4 (Web Text))

Max Activating Token Index: 1004

Text #9

Max Range: 1.2557. Min Range: -1.2557

Max Act: 1.0273. Min Act: -0.0001

Data Index: 1228220 (C4 (Web Text))

Max Activating Token Index: 710

Text #10

Max Range: 1.2557. Min Range: -1.2557

Max Act: 1.0824. Min Act: -0.0001

Data Index: 1159065 (C4 (Web Text))

Max Activating Token Index: 747

Text #11

Max Range: 1.2557. Min Range: -1.2557

Max Act: 0.9540. Min Act: -0.0001

Data Index: 1291812 (C4 (Web Text))

Max Activating Token Index: 82

Text #12

Max Range: 1.2557. Min Range: -1.2557

Max Act: 1.0381. Min Act: -0.0001

Data Index: 280961 (C4 (Web Text))

Max Activating Token Index: 109

Text #13

Max Range: 1.2557. Min Range: -1.2557

Max Act: 0.9997. Min Act: -0.0001

Data Index: 157813 (C4 (Web Text))

Max Activating Token Index: 939

Text #14

Max Range: 1.2557. Min Range: -1.2557

Max Act: 1.0726. Min Act: -0.0001

Data Index: 91166 (C4 (Web Text))

Max Activating Token Index: 168

Text #15

Max Range: 1.2557. Min Range: -1.2557

Max Act: 0.9677. Min Act: -0.0001

Data Index: 278041 (C4 (Web Text))

Max Activating Token Index: 744

Text #16

Max Range: 1.2557. Min Range: -1.2557

Max Act: 0.8988. Min Act: -0.0001

Data Index: 238444 (C4 (Web Text))

Max Activating Token Index: 436

Text #17

Max Range: 1.2557. Min Range: -1.2557

Max Act: 0.9723. Min Act: -0.0001

Data Index: 217105 (C4 (Web Text))

Max Activating Token Index: 811

Text #18

Max Range: 1.2557. Min Range: -1.2557

Max Act: 1.0000. Min Act: -0.0001

Data Index: 1157043 (C4 (Web Text))

Max Activating Token Index: 609

Text #19

Max Range: 1.2557. Min Range: -1.2557

Max Act: 0.8317. Min Act: -0.0001

Data Index: 1219877 (C4 (Web Text))

Max Activating Token Index: 627