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

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

Neuron 3892 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.1021. Min Act: -0.0000

Data Index: 49813 (C4 (Web Text))

Max Activating Token Index: 61

Text #1

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0832. Min Act: -0.0000

Data Index: 1185028 (C4 (Web Text))

Max Activating Token Index: 199

Text #2

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0820. Min Act: -0.0000

Data Index: 2871 (C4 (Web Text))

Max Activating Token Index: 272

Text #3

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0751. Min Act: -0.0000

Data Index: 71596 (C4 (Web Text))

Max Activating Token Index: 969

Text #4

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0708. Min Act: -0.0000

Data Index: 1072645 (C4 (Web Text))

Max Activating Token Index: 565

Text #5

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0728. Min Act: -0.0000

Data Index: 223803 (C4 (Web Text))

Max Activating Token Index: 161

Text #6

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0741. Min Act: -0.0000

Data Index: 647654 (C4 (Web Text))

Max Activating Token Index: 679

Text #7

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0659. Min Act: -0.0000

Data Index: 989965 (C4 (Web Text))

Max Activating Token Index: 474

Text #8

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0659. Min Act: -0.0000

Data Index: 847897 (C4 (Web Text))

Max Activating Token Index: 1021

Text #9

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0621. Min Act: -0.0000

Data Index: 93632 (C4 (Web Text))

Max Activating Token Index: 328

Text #10

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0612. Min Act: -0.0000

Data Index: 864680 (C4 (Web Text))

Max Activating Token Index: 692

Text #11

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0612. Min Act: -0.0000

Data Index: 263723 (C4 (Web Text))

Max Activating Token Index: 397

Text #12

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0634. Min Act: -0.0000

Data Index: 561333 (C4 (Web Text))

Max Activating Token Index: 560

Text #13

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0651. Min Act: -0.0000

Data Index: 636141 (C4 (Web Text))

Max Activating Token Index: 843

Text #14

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0638. Min Act: -0.0000

Data Index: 744872 (C4 (Web Text))

Max Activating Token Index: 185

Text #15

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0609. Min Act: -0.0000

Data Index: 628004 (C4 (Web Text))

Max Activating Token Index: 983

Text #16

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0632. Min Act: -0.0000

Data Index: 479891 (C4 (Web Text))

Max Activating Token Index: 644

Text #17

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0605. Min Act: -0.0000

Data Index: 1655819 (Python Code)

Max Activating Token Index: 96

Text #18

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0597. Min Act: -0.0000

Data Index: 206278 (C4 (Web Text))

Max Activating Token Index: 936

Text #19

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0595. Min Act: -0.0000

Data Index: 1523616 (Python Code)

Max Activating Token Index: 919