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

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

Neuron 2810 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5359. Min Range: -1.5359

Max Act: 1.4147. Min Act: -0.0000

Data Index: 1350288 (C4 (Web Text))

Max Activating Token Index: 818

Text #1

Max Range: 1.5359. Min Range: -1.5359

Max Act: 1.2603. Min Act: -0.0000

Data Index: 1546134 (Python Code)

Max Activating Token Index: 810

Text #2

Max Range: 1.5359. Min Range: -1.5359

Max Act: 1.5359. Min Act: -0.0000

Data Index: 1152931 (C4 (Web Text))

Max Activating Token Index: 956

Text #3

Max Range: 1.5359. Min Range: -1.5359

Max Act: 1.4071. Min Act: -0.0000

Data Index: 683775 (C4 (Web Text))

Max Activating Token Index: 644

Text #4

Max Range: 1.5359. Min Range: -1.5359

Max Act: 1.1556. Min Act: -0.0000

Data Index: 1317058 (C4 (Web Text))

Max Activating Token Index: 948

Text #5

Max Range: 1.5359. Min Range: -1.5359

Max Act: 1.2733. Min Act: -0.0000

Data Index: 1109940 (C4 (Web Text))

Max Activating Token Index: 838

Text #6

Max Range: 1.5359. Min Range: -1.5359

Max Act: 1.2067. Min Act: -0.0000

Data Index: 1263232 (C4 (Web Text))

Max Activating Token Index: 730

Text #7

Max Range: 1.5359. Min Range: -1.5359

Max Act: 1.1508. Min Act: -0.0000

Data Index: 1353245 (C4 (Web Text))

Max Activating Token Index: 924

Text #8

Max Range: 1.5359. Min Range: -1.5359

Max Act: 1.1323. Min Act: -0.0000

Data Index: 1226396 (C4 (Web Text))

Max Activating Token Index: 87

Text #9

Max Range: 1.5359. Min Range: -1.5359

Max Act: 1.1305. Min Act: -0.0000

Data Index: 696281 (C4 (Web Text))

Max Activating Token Index: 351

Text #10

Max Range: 1.5359. Min Range: -1.5359

Max Act: 1.1603. Min Act: -0.0000

Data Index: 620882 (C4 (Web Text))

Max Activating Token Index: 261

Text #11

Max Range: 1.5359. Min Range: -1.5359

Max Act: 0.9671. Min Act: -0.0000

Data Index: 1388412 (Python Code)

Max Activating Token Index: 112

Text #12

Max Range: 1.5359. Min Range: -1.5359

Max Act: 1.0545. Min Act: -0.0000

Data Index: 798325 (C4 (Web Text))

Max Activating Token Index: 599

Text #13

Max Range: 1.5359. Min Range: -1.5359

Max Act: 0.8693. Min Act: -0.0000

Data Index: 1412906 (Python Code)

Max Activating Token Index: 600

Text #14

Max Range: 1.5359. Min Range: -1.5359

Max Act: 0.9444. Min Act: -0.0000

Data Index: 1148426 (C4 (Web Text))

Max Activating Token Index: 676

Text #15

Max Range: 1.5359. Min Range: -1.5359

Max Act: 0.9048. Min Act: -0.0000

Data Index: 1329722 (C4 (Web Text))

Max Activating Token Index: 592

Text #16

Max Range: 1.5359. Min Range: -1.5359

Max Act: 0.8922. Min Act: -0.0000

Data Index: 728641 (C4 (Web Text))

Max Activating Token Index: 57

Text #17

Max Range: 1.5359. Min Range: -1.5359

Max Act: 0.8560. Min Act: -0.0000

Data Index: 1083421 (C4 (Web Text))

Max Activating Token Index: 248

Text #18

Max Range: 1.5359. Min Range: -1.5359

Max Act: 0.9236. Min Act: -0.0000

Data Index: 1243109 (C4 (Web Text))

Max Activating Token Index: 915

Text #19

Max Range: 1.5359. Min Range: -1.5359

Max Act: 0.8222. Min Act: -0.0000

Data Index: 1157323 (C4 (Web Text))

Max Activating Token Index: 814