Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1538 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0796. Min Act: -0.0005

Data Index: 622048 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0777. Min Act: -0.0005

Data Index: 432524 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0771. Min Act: -0.0005

Data Index: 1382726 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0770. Min Act: -0.0005

Data Index: 78066 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0759. Min Act: -0.0005

Data Index: 526316 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0756. Min Act: -0.0004

Data Index: 1576336 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0733. Min Act: -0.0004

Data Index: 1400310 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0748. Min Act: -0.0005

Data Index: 1441398 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0744. Min Act: -0.0005

Data Index: 1224478 (C4 (Web Text))

Max Activating Token Index: 2

Text #9

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0728. Min Act: -0.0005

Data Index: 829882 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0649. Min Act: -0.0005

Data Index: 1156238 (C4 (Web Text))

Max Activating Token Index: 910

Text #11

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0721. Min Act: -0.0005

Data Index: 1397763 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0719. Min Act: -0.0005

Data Index: 1598984 (Python Code)

Max Activating Token Index: 508

Text #13

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0686. Min Act: -0.0004

Data Index: 1655523 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0711. Min Act: -0.0004

Data Index: 1471053 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0712. Min Act: -0.0005

Data Index: 459264 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0722. Min Act: -0.0005

Data Index: 1360957 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0694. Min Act: -0.0005

Data Index: 1524926 (Python Code)

Max Activating Token Index: 1023

Text #18

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0696. Min Act: -0.0005

Data Index: 591316 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0675. Min Act: -0.0004

Data Index: 1429670 (Python Code)

Max Activating Token Index: 1023