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

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

Neuron 2892 in Layer 0

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: 0.9389. Min Range: -0.9389

Max Act: 0.9389. Min Act: -0.0001

Data Index: 1535616 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.9389. Min Range: -0.9389

Max Act: 0.8688. Min Act: -0.0000

Data Index: 1503521 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 0.9389. Min Range: -0.9389

Max Act: 0.7913. Min Act: -0.0000

Data Index: 1647274 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 0.9389. Min Range: -0.9389

Max Act: 0.7865. Min Act: -0.0000

Data Index: 1439259 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 0.9389. Min Range: -0.9389

Max Act: 0.7804. Min Act: -0.0000

Data Index: 1578165 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 0.9389. Min Range: -0.9389

Max Act: 0.7690. Min Act: -0.0000

Data Index: 1461631 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 0.9389. Min Range: -0.9389

Max Act: 0.7762. Min Act: -0.0000

Data Index: 1440716 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 0.9389. Min Range: -0.9389

Max Act: 0.7788. Min Act: -0.0001

Data Index: 1508935 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 0.9389. Min Range: -0.9389

Max Act: 0.7475. Min Act: -0.0001

Data Index: 1513887 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 0.9389. Min Range: -0.9389

Max Act: 0.7502. Min Act: -0.0001

Data Index: 1537837 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 0.9389. Min Range: -0.9389

Max Act: 0.7315. Min Act: -0.0001

Data Index: 1397013 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 0.9389. Min Range: -0.9389

Max Act: 0.7220. Min Act: -0.0001

Data Index: 1430135 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 0.9389. Min Range: -0.9389

Max Act: 0.7082. Min Act: -0.0000

Data Index: 1361546 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 0.9389. Min Range: -0.9389

Max Act: 0.7158. Min Act: -0.0000

Data Index: 1453870 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 0.9389. Min Range: -0.9389

Max Act: 0.7092. Min Act: -0.0001

Data Index: 1519484 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 0.9389. Min Range: -0.9389

Max Act: 0.7195. Min Act: -0.0001

Data Index: 1542745 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 0.9389. Min Range: -0.9389

Max Act: 0.6904. Min Act: -0.0001

Data Index: 1375003 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 0.9389. Min Range: -0.9389

Max Act: 0.7048. Min Act: -0.0001

Data Index: 1561148 (Python Code)

Max Activating Token Index: 1023

Text #18

Max Range: 0.9389. Min Range: -0.9389

Max Act: 0.6775. Min Act: -0.0001

Data Index: 1531946 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 0.9389. Min Range: -0.9389

Max Act: 0.6760. Min Act: -0.0001

Data Index: 1560843 (Python Code)

Max Activating Token Index: 1023