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

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

Neuron 3021 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6055. Min Range: -2.6055

Max Act: 2.6055. Min Act: -0.0000

Data Index: 1533613 (Python Code)

Max Activating Token Index: 844

Text #1

Max Range: 2.6055. Min Range: -2.6055

Max Act: 2.6024. Min Act: -0.0000

Data Index: 1409667 (Python Code)

Max Activating Token Index: 426

Text #2

Max Range: 2.6055. Min Range: -2.6055

Max Act: 2.4799. Min Act: -0.0000

Data Index: 1516672 (Python Code)

Max Activating Token Index: 110

Text #3

Max Range: 2.6055. Min Range: -2.6055

Max Act: 2.2771. Min Act: -0.0000

Data Index: 1377804 (Python Code)

Max Activating Token Index: 883

Text #4

Max Range: 2.6055. Min Range: -2.6055

Max Act: 2.2277. Min Act: -0.0000

Data Index: 73595 (C4 (Web Text))

Max Activating Token Index: 857

Text #5

Max Range: 2.6055. Min Range: -2.6055

Max Act: 2.2386. Min Act: -0.0000

Data Index: 1634249 (Python Code)

Max Activating Token Index: 1014

Text #6

Max Range: 2.6055. Min Range: -2.6055

Max Act: 2.1321. Min Act: -0.0000

Data Index: 898979 (C4 (Web Text))

Max Activating Token Index: 640

Text #7

Max Range: 2.6055. Min Range: -2.6055

Max Act: 1.9000. Min Act: -0.0000

Data Index: 1350039 (C4 (Web Text))

Max Activating Token Index: 253

Text #8

Max Range: 2.6055. Min Range: -2.6055

Max Act: 2.1218. Min Act: -0.0000

Data Index: 1430670 (Python Code)

Max Activating Token Index: 54

Text #9

Max Range: 2.6055. Min Range: -2.6055

Max Act: 1.8933. Min Act: -0.0000

Data Index: 1616611 (Python Code)

Max Activating Token Index: 619

Text #10

Max Range: 2.6055. Min Range: -2.6055

Max Act: 2.2119. Min Act: -0.0000

Data Index: 1548467 (Python Code)

Max Activating Token Index: 45

Text #11

Max Range: 2.6055. Min Range: -2.6055

Max Act: 2.0727. Min Act: -0.0000

Data Index: 1468984 (Python Code)

Max Activating Token Index: 19

Text #12

Max Range: 2.6055. Min Range: -2.6055

Max Act: 1.9479. Min Act: -0.0000

Data Index: 1624132 (Python Code)

Max Activating Token Index: 132

Text #13

Max Range: 2.6055. Min Range: -2.6055

Max Act: 2.0696. Min Act: -0.0000

Data Index: 423298 (C4 (Web Text))

Max Activating Token Index: 592

Text #14

Max Range: 2.6055. Min Range: -2.6055

Max Act: 2.0356. Min Act: -0.0000

Data Index: 1527142 (Python Code)

Max Activating Token Index: 992

Text #15

Max Range: 2.6055. Min Range: -2.6055

Max Act: 2.1515. Min Act: -0.0000

Data Index: 1491273 (Python Code)

Max Activating Token Index: 60

Text #16

Max Range: 2.6055. Min Range: -2.6055

Max Act: 2.0294. Min Act: -0.0000

Data Index: 1611783 (Python Code)

Max Activating Token Index: 809

Text #17

Max Range: 2.6055. Min Range: -2.6055

Max Act: 2.0938. Min Act: -0.0000

Data Index: 1407975 (Python Code)

Max Activating Token Index: 76

Text #18

Max Range: 2.6055. Min Range: -2.6055

Max Act: 1.9716. Min Act: -0.0000

Data Index: 1496842 (Python Code)

Max Activating Token Index: 189

Text #19

Max Range: 2.6055. Min Range: -2.6055

Max Act: 1.9543. Min Act: -0.0000

Data Index: 1426764 (Python Code)

Max Activating Token Index: 705