Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3189 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.3294. Min Act: -0.0001

Data Index: 1627086 (Python Code)

Max Activating Token Index: 965

Text #1

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.3115. Min Act: -0.0000

Data Index: 1492823 (Python Code)

Max Activating Token Index: 48

Text #2

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.3045. Min Act: -0.0001

Data Index: 1627301 (Python Code)

Max Activating Token Index: 260

Text #3

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.3017. Min Act: -0.0001

Data Index: 1406372 (Python Code)

Max Activating Token Index: 225

Text #4

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2997. Min Act: -0.0000

Data Index: 1545866 (Python Code)

Max Activating Token Index: 988

Text #5

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.3029. Min Act: -0.0001

Data Index: 1482569 (Python Code)

Max Activating Token Index: 75

Text #6

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.3026. Min Act: -0.0000

Data Index: 1469572 (Python Code)

Max Activating Token Index: 1008

Text #7

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.3010. Min Act: -0.0001

Data Index: 1588554 (Python Code)

Max Activating Token Index: 143

Text #8

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2715. Min Act: -0.0001

Data Index: 1518820 (Python Code)

Max Activating Token Index: 648

Text #9

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2513. Min Act: -0.0001

Data Index: 1624736 (Python Code)

Max Activating Token Index: 706

Text #10

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2695. Min Act: -0.0001

Data Index: 1616310 (Python Code)

Max Activating Token Index: 4

Text #11

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2749. Min Act: -0.0000

Data Index: 1610799 (Python Code)

Max Activating Token Index: 252

Text #12

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2763. Min Act: -0.0000

Data Index: 1593602 (Python Code)

Max Activating Token Index: 316

Text #13

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2651. Min Act: -0.0001

Data Index: 1454121 (Python Code)

Max Activating Token Index: 823

Text #14

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2697. Min Act: -0.0001

Data Index: 1548608 (Python Code)

Max Activating Token Index: 963

Text #15

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2690. Min Act: -0.0001

Data Index: 1577523 (Python Code)

Max Activating Token Index: 607

Text #16

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2686. Min Act: -0.0000

Data Index: 1508101 (Python Code)

Max Activating Token Index: 217

Text #17

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2698. Min Act: -0.0001

Data Index: 1508651 (Python Code)

Max Activating Token Index: 244

Text #18

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2780. Min Act: -0.0000

Data Index: 1540150 (Python Code)

Max Activating Token Index: 33

Text #19

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2583. Min Act: -0.0000

Data Index: 1518202 (Python Code)

Max Activating Token Index: 45