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

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

Neuron 3697 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.1046. Min Act: -0.0000

Data Index: 1112892 (C4 (Web Text))

Max Activating Token Index: 32

Text #1

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0987. Min Act: -0.0000

Data Index: 926860 (C4 (Web Text))

Max Activating Token Index: 739

Text #2

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0925. Min Act: -0.0000

Data Index: 203522 (C4 (Web Text))

Max Activating Token Index: 9

Text #3

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0871. Min Act: -0.0001

Data Index: 853648 (C4 (Web Text))

Max Activating Token Index: 8

Text #4

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0829. Min Act: -0.0001

Data Index: 190001 (C4 (Web Text))

Max Activating Token Index: 616

Text #5

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0885. Min Act: -0.0000

Data Index: 1237080 (C4 (Web Text))

Max Activating Token Index: 92

Text #6

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0803. Min Act: -0.0000

Data Index: 281673 (C4 (Web Text))

Max Activating Token Index: 868

Text #7

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0861. Min Act: -0.0000

Data Index: 236715 (C4 (Web Text))

Max Activating Token Index: 5

Text #8

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0798. Min Act: -0.0001

Data Index: 499850 (C4 (Web Text))

Max Activating Token Index: 382

Text #9

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0807. Min Act: -0.0001

Data Index: 1562860 (Python Code)

Max Activating Token Index: 643

Text #10

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0847. Min Act: -0.0000

Data Index: 224529 (C4 (Web Text))

Max Activating Token Index: 615

Text #11

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0818. Min Act: -0.0001

Data Index: 1479652 (Python Code)

Max Activating Token Index: 997

Text #12

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0787. Min Act: -0.0000

Data Index: 405132 (C4 (Web Text))

Max Activating Token Index: 648

Text #13

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0810. Min Act: -0.0001

Data Index: 775254 (C4 (Web Text))

Max Activating Token Index: 756

Text #14

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0774. Min Act: -0.0001

Data Index: 602564 (C4 (Web Text))

Max Activating Token Index: 988

Text #15

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0743. Min Act: -0.0000

Data Index: 269512 (C4 (Web Text))

Max Activating Token Index: 257

Text #16

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0776. Min Act: -0.0000

Data Index: 1134859 (C4 (Web Text))

Max Activating Token Index: 220

Text #17

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0797. Min Act: -0.0001

Data Index: 1093127 (C4 (Web Text))

Max Activating Token Index: 655

Text #18

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0760. Min Act: -0.0001

Data Index: 1112315 (C4 (Web Text))

Max Activating Token Index: 578

Text #19

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0760. Min Act: -0.0000

Data Index: 12766 (C4 (Web Text))

Max Activating Token Index: 597