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

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

Neuron 1695 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7897. Min Range: -2.7897

Max Act: 2.7897. Min Act: -0.0000

Data Index: 1548476 (Python Code)

Max Activating Token Index: 820

Text #1

Max Range: 2.7897. Min Range: -2.7897

Max Act: 2.4358. Min Act: -0.0000

Data Index: 1553818 (Python Code)

Max Activating Token Index: 421

Text #2

Max Range: 2.7897. Min Range: -2.7897

Max Act: 2.3963. Min Act: -0.0000

Data Index: 1466718 (Python Code)

Max Activating Token Index: 185

Text #3

Max Range: 2.7897. Min Range: -2.7897

Max Act: 1.9904. Min Act: -0.0000

Data Index: 1430840 (Python Code)

Max Activating Token Index: 629

Text #4

Max Range: 2.7897. Min Range: -2.7897

Max Act: 2.0550. Min Act: -0.0000

Data Index: 1599979 (Python Code)

Max Activating Token Index: 494

Text #5

Max Range: 2.7897. Min Range: -2.7897

Max Act: 1.8857. Min Act: -0.0000

Data Index: 1441248 (Python Code)

Max Activating Token Index: 781

Text #6

Max Range: 2.7897. Min Range: -2.7897

Max Act: 2.0736. Min Act: -0.0000

Data Index: 1467646 (Python Code)

Max Activating Token Index: 396

Text #7

Max Range: 2.7897. Min Range: -2.7897

Max Act: 1.5571. Min Act: -0.0000

Data Index: 1406644 (Python Code)

Max Activating Token Index: 737

Text #8

Max Range: 2.7897. Min Range: -2.7897

Max Act: 1.9549. Min Act: -0.0000

Data Index: 1560343 (Python Code)

Max Activating Token Index: 363

Text #9

Max Range: 2.7897. Min Range: -2.7897

Max Act: 1.9470. Min Act: -0.0000

Data Index: 1515474 (Python Code)

Max Activating Token Index: 938

Text #10

Max Range: 2.7897. Min Range: -2.7897

Max Act: 1.8584. Min Act: -0.0000

Data Index: 1451555 (Python Code)

Max Activating Token Index: 806

Text #11

Max Range: 2.7897. Min Range: -2.7897

Max Act: 1.9106. Min Act: -0.0000

Data Index: 1557476 (Python Code)

Max Activating Token Index: 522

Text #12

Max Range: 2.7897. Min Range: -2.7897

Max Act: 1.6030. Min Act: -0.0000

Data Index: 1629279 (Python Code)

Max Activating Token Index: 633

Text #13

Max Range: 2.7897. Min Range: -2.7897

Max Act: 1.5008. Min Act: -0.0000

Data Index: 1639093 (Python Code)

Max Activating Token Index: 683

Text #14

Max Range: 2.7897. Min Range: -2.7897

Max Act: 1.6892. Min Act: -0.0000

Data Index: 1639258 (Python Code)

Max Activating Token Index: 157

Text #15

Max Range: 2.7897. Min Range: -2.7897

Max Act: 1.6962. Min Act: -0.0000

Data Index: 1404476 (Python Code)

Max Activating Token Index: 695

Text #16

Max Range: 2.7897. Min Range: -2.7897

Max Act: 1.6765. Min Act: -0.0000

Data Index: 1463917 (Python Code)

Max Activating Token Index: 1014

Text #17

Max Range: 2.7897. Min Range: -2.7897

Max Act: 1.7150. Min Act: -0.0000

Data Index: 1403361 (Python Code)

Max Activating Token Index: 787

Text #18

Max Range: 2.7897. Min Range: -2.7897

Max Act: 1.8037. Min Act: -0.0000

Data Index: 1379336 (Python Code)

Max Activating Token Index: 309

Text #19

Max Range: 2.7897. Min Range: -2.7897

Max Act: 1.6044. Min Act: -0.0000

Data Index: 1606570 (Python Code)

Max Activating Token Index: 642