Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4678 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0645. Min Range: -1.0645

Max Act: 1.0645. Min Act: -0.0000

Data Index: 1216192 (C4 (Web Text))

Max Activating Token Index: 142

Text #1

Max Range: 1.0645. Min Range: -1.0645

Max Act: 0.8979. Min Act: -0.0000

Data Index: 388942 (C4 (Web Text))

Max Activating Token Index: 187

Text #2

Max Range: 1.0645. Min Range: -1.0645

Max Act: 0.7584. Min Act: -0.0000

Data Index: 689623 (C4 (Web Text))

Max Activating Token Index: 672

Text #3

Max Range: 1.0645. Min Range: -1.0645

Max Act: 0.7392. Min Act: -0.0000

Data Index: 1229853 (C4 (Web Text))

Max Activating Token Index: 408

Text #4

Max Range: 1.0645. Min Range: -1.0645

Max Act: 0.7819. Min Act: -0.0000

Data Index: 207514 (C4 (Web Text))

Max Activating Token Index: 1017

Text #5

Max Range: 1.0645. Min Range: -1.0645

Max Act: 0.6969. Min Act: -0.0000

Data Index: 710227 (C4 (Web Text))

Max Activating Token Index: 917

Text #6

Max Range: 1.0645. Min Range: -1.0645

Max Act: 0.7342. Min Act: -0.0000

Data Index: 1215900 (C4 (Web Text))

Max Activating Token Index: 637

Text #7

Max Range: 1.0645. Min Range: -1.0645

Max Act: 0.6748. Min Act: -0.0000

Data Index: 453656 (C4 (Web Text))

Max Activating Token Index: 576

Text #8

Max Range: 1.0645. Min Range: -1.0645

Max Act: 0.6537. Min Act: -0.0000

Data Index: 729446 (C4 (Web Text))

Max Activating Token Index: 824

Text #9

Max Range: 1.0645. Min Range: -1.0645

Max Act: 0.6638. Min Act: -0.0000

Data Index: 235805 (C4 (Web Text))

Max Activating Token Index: 853

Text #10

Max Range: 1.0645. Min Range: -1.0645

Max Act: 0.7012. Min Act: -0.0000

Data Index: 194041 (C4 (Web Text))

Max Activating Token Index: 394

Text #11

Max Range: 1.0645. Min Range: -1.0645

Max Act: 0.6593. Min Act: -0.0000

Data Index: 136258 (C4 (Web Text))

Max Activating Token Index: 590

Text #12

Max Range: 1.0645. Min Range: -1.0645

Max Act: 0.6464. Min Act: -0.0000

Data Index: 905041 (C4 (Web Text))

Max Activating Token Index: 43

Text #13

Max Range: 1.0645. Min Range: -1.0645

Max Act: 0.6477. Min Act: -0.0000

Data Index: 769021 (C4 (Web Text))

Max Activating Token Index: 529

Text #14

Max Range: 1.0645. Min Range: -1.0645

Max Act: 0.6505. Min Act: -0.0000

Data Index: 574595 (C4 (Web Text))

Max Activating Token Index: 608

Text #15

Max Range: 1.0645. Min Range: -1.0645

Max Act: 0.6342. Min Act: -0.0000

Data Index: 149919 (C4 (Web Text))

Max Activating Token Index: 35

Text #16

Max Range: 1.0645. Min Range: -1.0645

Max Act: 0.6212. Min Act: -0.0000

Data Index: 964217 (C4 (Web Text))

Max Activating Token Index: 638

Text #17

Max Range: 1.0645. Min Range: -1.0645

Max Act: 0.6196. Min Act: -0.0000

Data Index: 120581 (C4 (Web Text))

Max Activating Token Index: 383

Text #18

Max Range: 1.0645. Min Range: -1.0645

Max Act: 0.6284. Min Act: -0.0000

Data Index: 1161151 (C4 (Web Text))

Max Activating Token Index: 653

Text #19

Max Range: 1.0645. Min Range: -1.0645

Max Act: 0.6139. Min Act: -0.0000

Data Index: 1076597 (C4 (Web Text))

Max Activating Token Index: 782