Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1264 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.1352. Min Act: -0.0001

Data Index: 455864 (C4 (Web Text))

Max Activating Token Index: 824

Text #1

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.1413. Min Act: -0.0001

Data Index: 148225 (C4 (Web Text))

Max Activating Token Index: 905

Text #2

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.1513. Min Act: -0.0001

Data Index: 523137 (C4 (Web Text))

Max Activating Token Index: 812

Text #3

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.1326. Min Act: -0.0001

Data Index: 696470 (C4 (Web Text))

Max Activating Token Index: 619

Text #4

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.1169. Min Act: -0.0001

Data Index: 375681 (C4 (Web Text))

Max Activating Token Index: 846

Text #5

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.1407. Min Act: -0.0001

Data Index: 457642 (C4 (Web Text))

Max Activating Token Index: 87

Text #6

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.1205. Min Act: -0.0001

Data Index: 207370 (C4 (Web Text))

Max Activating Token Index: 71

Text #7

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.1089. Min Act: -0.0001

Data Index: 499295 (C4 (Web Text))

Max Activating Token Index: 343

Text #8

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.1299. Min Act: -0.0001

Data Index: 455872 (C4 (Web Text))

Max Activating Token Index: 524

Text #9

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.1295. Min Act: -0.0001

Data Index: 98747 (C4 (Web Text))

Max Activating Token Index: 852

Text #10

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.1098. Min Act: -0.0001

Data Index: 202111 (C4 (Web Text))

Max Activating Token Index: 505

Text #11

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.1216. Min Act: -0.0001

Data Index: 1208858 (C4 (Web Text))

Max Activating Token Index: 473

Text #12

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.1051. Min Act: -0.0001

Data Index: 1243540 (C4 (Web Text))

Max Activating Token Index: 998

Text #13

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.1087. Min Act: -0.0001

Data Index: 877429 (C4 (Web Text))

Max Activating Token Index: 493

Text #14

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.1072. Min Act: -0.0001

Data Index: 255357 (C4 (Web Text))

Max Activating Token Index: 48

Text #15

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.0970. Min Act: -0.0001

Data Index: 533788 (C4 (Web Text))

Max Activating Token Index: 873

Text #16

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.1076. Min Act: -0.0001

Data Index: 945226 (C4 (Web Text))

Max Activating Token Index: 22

Text #17

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.0973. Min Act: -0.0001

Data Index: 624158 (C4 (Web Text))

Max Activating Token Index: 45

Text #18

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.1007. Min Act: -0.0001

Data Index: 397841 (C4 (Web Text))

Max Activating Token Index: 729

Text #19

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.1002. Min Act: -0.0001

Data Index: 536765 (C4 (Web Text))

Max Activating Token Index: 940