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

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

Neuron 504 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6595. Min Range: -2.6595

Max Act: 2.6595. Min Act: -0.0000

Data Index: 1610982 (Python Code)

Max Activating Token Index: 635

Text #1

Max Range: 2.6595. Min Range: -2.6595

Max Act: 1.9815. Min Act: -0.0000

Data Index: 1542848 (Python Code)

Max Activating Token Index: 909

Text #2

Max Range: 2.6595. Min Range: -2.6595

Max Act: 1.7008. Min Act: -0.0000

Data Index: 1531601 (Python Code)

Max Activating Token Index: 809

Text #3

Max Range: 2.6595. Min Range: -2.6595

Max Act: 1.5967. Min Act: -0.0000

Data Index: 1585860 (Python Code)

Max Activating Token Index: 784

Text #4

Max Range: 2.6595. Min Range: -2.6595

Max Act: 1.9870. Min Act: -0.0000

Data Index: 1475920 (Python Code)

Max Activating Token Index: 941

Text #5

Max Range: 2.6595. Min Range: -2.6595

Max Act: 1.9922. Min Act: -0.0000

Data Index: 1495930 (Python Code)

Max Activating Token Index: 541

Text #6

Max Range: 2.6595. Min Range: -2.6595

Max Act: 1.9647. Min Act: -0.0000

Data Index: 1423726 (Python Code)

Max Activating Token Index: 410

Text #7

Max Range: 2.6595. Min Range: -2.6595

Max Act: 2.1319. Min Act: -0.0000

Data Index: 1634603 (Python Code)

Max Activating Token Index: 822

Text #8

Max Range: 2.6595. Min Range: -2.6595

Max Act: 1.8677. Min Act: -0.0000

Data Index: 1409331 (Python Code)

Max Activating Token Index: 925

Text #9

Max Range: 2.6595. Min Range: -2.6595

Max Act: 1.9711. Min Act: -0.0000

Data Index: 1369933 (Python Code)

Max Activating Token Index: 582

Text #10

Max Range: 2.6595. Min Range: -2.6595

Max Act: 1.7329. Min Act: -0.0000

Data Index: 1423830 (Python Code)

Max Activating Token Index: 993

Text #11

Max Range: 2.6595. Min Range: -2.6595

Max Act: 1.8113. Min Act: -0.0000

Data Index: 1351929 (C4 (Web Text))

Max Activating Token Index: 110

Text #12

Max Range: 2.6595. Min Range: -2.6595

Max Act: 1.7132. Min Act: -0.0000

Data Index: 952089 (C4 (Web Text))

Max Activating Token Index: 97

Text #13

Max Range: 2.6595. Min Range: -2.6595

Max Act: 1.6911. Min Act: -0.0000

Data Index: 1438932 (Python Code)

Max Activating Token Index: 658

Text #14

Max Range: 2.6595. Min Range: -2.6595

Max Act: 1.5782. Min Act: -0.0000

Data Index: 1507904 (Python Code)

Max Activating Token Index: 592

Text #15

Max Range: 2.6595. Min Range: -2.6595

Max Act: 1.6754. Min Act: -0.0000

Data Index: 1516264 (Python Code)

Max Activating Token Index: 631

Text #16

Max Range: 2.6595. Min Range: -2.6595

Max Act: 1.5717. Min Act: -0.0000

Data Index: 582257 (C4 (Web Text))

Max Activating Token Index: 214

Text #17

Max Range: 2.6595. Min Range: -2.6595

Max Act: 1.4739. Min Act: -0.0000

Data Index: 457327 (C4 (Web Text))

Max Activating Token Index: 181

Text #18

Max Range: 2.6595. Min Range: -2.6595

Max Act: 1.3994. Min Act: -0.0000

Data Index: 1641419 (Python Code)

Max Activating Token Index: 771

Text #19

Max Range: 2.6595. Min Range: -2.6595

Max Act: 1.3465. Min Act: -0.0000

Data Index: 1305036 (C4 (Web Text))

Max Activating Token Index: 818