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

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

Neuron 1678 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8738. Min Range: -0.8738

Max Act: 0.8738. Min Act: -0.0000

Data Index: 499283 (C4 (Web Text))

Max Activating Token Index: 588

Text #1

Max Range: 0.8738. Min Range: -0.8738

Max Act: 0.7796. Min Act: -0.0000

Data Index: 1297159 (C4 (Web Text))

Max Activating Token Index: 708

Text #2

Max Range: 0.8738. Min Range: -0.8738

Max Act: 0.7078. Min Act: -0.0000

Data Index: 960223 (C4 (Web Text))

Max Activating Token Index: 721

Text #3

Max Range: 0.8738. Min Range: -0.8738

Max Act: 0.7235. Min Act: -0.0000

Data Index: 271626 (C4 (Web Text))

Max Activating Token Index: 1008

Text #4

Max Range: 0.8738. Min Range: -0.8738

Max Act: 0.6906. Min Act: -0.0000

Data Index: 1302204 (C4 (Web Text))

Max Activating Token Index: 398

Text #5

Max Range: 0.8738. Min Range: -0.8738

Max Act: 0.6527. Min Act: -0.0000

Data Index: 736202 (C4 (Web Text))

Max Activating Token Index: 155

Text #6

Max Range: 0.8738. Min Range: -0.8738

Max Act: 0.6872. Min Act: -0.0000

Data Index: 1089934 (C4 (Web Text))

Max Activating Token Index: 51

Text #7

Max Range: 0.8738. Min Range: -0.8738

Max Act: 0.6536. Min Act: -0.0000

Data Index: 188688 (C4 (Web Text))

Max Activating Token Index: 104

Text #8

Max Range: 0.8738. Min Range: -0.8738

Max Act: 0.6094. Min Act: -0.0000

Data Index: 183685 (C4 (Web Text))

Max Activating Token Index: 806

Text #9

Max Range: 0.8738. Min Range: -0.8738

Max Act: 0.6672. Min Act: -0.0000

Data Index: 25225 (C4 (Web Text))

Max Activating Token Index: 637

Text #10

Max Range: 0.8738. Min Range: -0.8738

Max Act: 0.6757. Min Act: -0.0000

Data Index: 1116546 (C4 (Web Text))

Max Activating Token Index: 337

Text #11

Max Range: 0.8738. Min Range: -0.8738

Max Act: 0.6143. Min Act: -0.0000

Data Index: 847281 (C4 (Web Text))

Max Activating Token Index: 634

Text #12

Max Range: 0.8738. Min Range: -0.8738

Max Act: 0.6395. Min Act: -0.0000

Data Index: 853637 (C4 (Web Text))

Max Activating Token Index: 988

Text #13

Max Range: 0.8738. Min Range: -0.8738

Max Act: 0.6277. Min Act: -0.0000

Data Index: 2609 (C4 (Web Text))

Max Activating Token Index: 985

Text #14

Max Range: 0.8738. Min Range: -0.8738

Max Act: 0.6012. Min Act: -0.0000

Data Index: 846404 (C4 (Web Text))

Max Activating Token Index: 666

Text #15

Max Range: 0.8738. Min Range: -0.8738

Max Act: 0.6506. Min Act: -0.0000

Data Index: 633911 (C4 (Web Text))

Max Activating Token Index: 688

Text #16

Max Range: 0.8738. Min Range: -0.8738

Max Act: 0.6428. Min Act: -0.0000

Data Index: 1225470 (C4 (Web Text))

Max Activating Token Index: 353

Text #17

Max Range: 0.8738. Min Range: -0.8738

Max Act: 0.6123. Min Act: -0.0000

Data Index: 522818 (C4 (Web Text))

Max Activating Token Index: 778

Text #18

Max Range: 0.8738. Min Range: -0.8738

Max Act: 0.6265. Min Act: -0.0000

Data Index: 1002510 (C4 (Web Text))

Max Activating Token Index: 4

Text #19

Max Range: 0.8738. Min Range: -0.8738

Max Act: 0.5868. Min Act: -0.0000

Data Index: 302190 (C4 (Web Text))

Max Activating Token Index: 464