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

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

Neuron 727 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: 0.0967. Min Range: -0.0967

Max Act: 0.0942. Min Act: -0.0002

Data Index: 556200 (C4 (Web Text))

Max Activating Token Index: 969

Text #1

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0967. Min Act: -0.0002

Data Index: 1368451 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0946. Min Act: -0.0002

Data Index: 1456000 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0811. Min Act: -0.0002

Data Index: 567756 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0795. Min Act: -0.0003

Data Index: 76937 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0818. Min Act: -0.0003

Data Index: 932664 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0858. Min Act: -0.0002

Data Index: 1433723 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0768. Min Act: -0.0002

Data Index: 920373 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0788. Min Act: -0.0002

Data Index: 1559594 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0798. Min Act: -0.0002

Data Index: 1579443 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0785. Min Act: -0.0002

Data Index: 298275 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0757. Min Act: -0.0002

Data Index: 68661 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0713. Min Act: -0.0002

Data Index: 1058202 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0721. Min Act: -0.0002

Data Index: 914860 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0711. Min Act: -0.0002

Data Index: 1620940 (Python Code)

Max Activating Token Index: 999

Text #15

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0703. Min Act: -0.0003

Data Index: 880644 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0676. Min Act: -0.0002

Data Index: 20438 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0707. Min Act: -0.0002

Data Index: 974641 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0666. Min Act: -0.0002

Data Index: 101260 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0677. Min Act: -0.0002

Data Index: 1498420 (Python Code)

Max Activating Token Index: 1023