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

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

Neuron 3978 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0938. Min Act: -0.0003

Data Index: 1229758 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0818. Min Act: -0.0003

Data Index: 1293298 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0779. Min Act: -0.0003

Data Index: 453548 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0777. Min Act: -0.0003

Data Index: 279049 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0740. Min Act: -0.0003

Data Index: 662194 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0789. Min Act: -0.0003

Data Index: 1330926 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0762. Min Act: -0.0003

Data Index: 78206 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0651. Min Act: -0.0003

Data Index: 1099001 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0693. Min Act: -0.0003

Data Index: 567363 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0690. Min Act: -0.0003

Data Index: 855056 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0716. Min Act: -0.0003

Data Index: 683737 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0682. Min Act: -0.0003

Data Index: 951995 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0710. Min Act: -0.0003

Data Index: 1003967 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0701. Min Act: -0.0003

Data Index: 957924 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0670. Min Act: -0.0003

Data Index: 977950 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0694. Min Act: -0.0003

Data Index: 91140 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0667. Min Act: -0.0003

Data Index: 207444 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0721. Min Act: -0.0004

Data Index: 549962 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0694. Min Act: -0.0003

Data Index: 673444 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0636. Min Act: -0.0003

Data Index: 1234367 (C4 (Web Text))

Max Activating Token Index: 1023