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

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

Neuron 5349 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 2.8591. Min Range: -2.8591

Max Act: 2.8591. Min Act: -0.0002

Data Index: 1456244 (Python Code)

Max Activating Token Index: 1

Text #1

Max Range: 2.8591. Min Range: -2.8591

Max Act: 2.8591. Min Act: -0.0002

Data Index: 1386485 (Python Code)

Max Activating Token Index: 1

Text #2

Max Range: 2.8591. Min Range: -2.8591

Max Act: 2.8591. Min Act: -0.0002

Data Index: 1423629 (Python Code)

Max Activating Token Index: 1

Text #3

Max Range: 2.8591. Min Range: -2.8591

Max Act: 2.8591. Min Act: -0.0002

Data Index: 1371842 (Python Code)

Max Activating Token Index: 1

Text #4

Max Range: 2.8591. Min Range: -2.8591

Max Act: 2.8591. Min Act: -0.0002

Data Index: 1565349 (Python Code)

Max Activating Token Index: 1

Text #5

Max Range: 2.8591. Min Range: -2.8591

Max Act: 2.8591. Min Act: -0.0002

Data Index: 1562754 (Python Code)

Max Activating Token Index: 1

Text #6

Max Range: 2.8591. Min Range: -2.8591

Max Act: 2.8591. Min Act: -0.0002

Data Index: 1370042 (Python Code)

Max Activating Token Index: 1

Text #7

Max Range: 2.8591. Min Range: -2.8591

Max Act: 2.8591. Min Act: -0.0002

Data Index: 1366291 (Python Code)

Max Activating Token Index: 1

Text #8

Max Range: 2.8591. Min Range: -2.8591

Max Act: 2.8591. Min Act: -0.0002

Data Index: 1391815 (Python Code)

Max Activating Token Index: 1

Text #9

Max Range: 2.8591. Min Range: -2.8591

Max Act: 2.8591. Min Act: -0.0002

Data Index: 1440413 (Python Code)

Max Activating Token Index: 1

Text #10

Max Range: 2.8591. Min Range: -2.8591

Max Act: 2.8591. Min Act: -0.0002

Data Index: 1557883 (Python Code)

Max Activating Token Index: 1

Text #11

Max Range: 2.8591. Min Range: -2.8591

Max Act: 2.8591. Min Act: -0.0002

Data Index: 1431280 (Python Code)

Max Activating Token Index: 1

Text #12

Max Range: 2.8591. Min Range: -2.8591

Max Act: 2.8591. Min Act: -0.0002

Data Index: 1554531 (Python Code)

Max Activating Token Index: 1

Text #13

Max Range: 2.8591. Min Range: -2.8591

Max Act: 2.8591. Min Act: -0.0002

Data Index: 1543497 (Python Code)

Max Activating Token Index: 1

Text #14

Max Range: 2.8591. Min Range: -2.8591

Max Act: 2.8591. Min Act: -0.0002

Data Index: 1409040 (Python Code)

Max Activating Token Index: 1

Text #15

Max Range: 2.8591. Min Range: -2.8591

Max Act: 2.8591. Min Act: -0.0002

Data Index: 1541800 (Python Code)

Max Activating Token Index: 1

Text #16

Max Range: 2.8591. Min Range: -2.8591

Max Act: 2.8591. Min Act: -0.0002

Data Index: 1541780 (Python Code)

Max Activating Token Index: 1

Text #17

Max Range: 2.8591. Min Range: -2.8591

Max Act: 2.8591. Min Act: -0.0002

Data Index: 1429176 (Python Code)

Max Activating Token Index: 1

Text #18

Max Range: 2.8591. Min Range: -2.8591

Max Act: 2.8591. Min Act: -0.0002

Data Index: 1455891 (Python Code)

Max Activating Token Index: 1

Text #19

Max Range: 2.8591. Min Range: -2.8591

Max Act: 2.8591. Min Act: -0.0002

Data Index: 1494806 (Python Code)

Max Activating Token Index: 1