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

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

Neuron 4748 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7966. Min Range: -1.7966

Max Act: 1.7966. Min Act: -0.0000

Data Index: 664403 (C4 (Web Text))

Max Activating Token Index: 242

Text #1

Max Range: 1.7966. Min Range: -1.7966

Max Act: 1.3608. Min Act: -0.0000

Data Index: 93145 (C4 (Web Text))

Max Activating Token Index: 160

Text #2

Max Range: 1.7966. Min Range: -1.7966

Max Act: 1.2753. Min Act: -0.0000

Data Index: 466811 (C4 (Web Text))

Max Activating Token Index: 844

Text #3

Max Range: 1.7966. Min Range: -1.7966

Max Act: 1.3017. Min Act: -0.0000

Data Index: 991003 (C4 (Web Text))

Max Activating Token Index: 640

Text #4

Max Range: 1.7966. Min Range: -1.7966

Max Act: 1.2477. Min Act: -0.0000

Data Index: 368009 (C4 (Web Text))

Max Activating Token Index: 966

Text #5

Max Range: 1.7966. Min Range: -1.7966

Max Act: 1.1998. Min Act: -0.0000

Data Index: 893718 (C4 (Web Text))

Max Activating Token Index: 651

Text #6

Max Range: 1.7966. Min Range: -1.7966

Max Act: 1.2045. Min Act: -0.0000

Data Index: 896288 (C4 (Web Text))

Max Activating Token Index: 310

Text #7

Max Range: 1.7966. Min Range: -1.7966

Max Act: 1.1621. Min Act: -0.0000

Data Index: 598746 (C4 (Web Text))

Max Activating Token Index: 446

Text #8

Max Range: 1.7966. Min Range: -1.7966

Max Act: 1.1663. Min Act: -0.0000

Data Index: 1200083 (C4 (Web Text))

Max Activating Token Index: 847

Text #9

Max Range: 1.7966. Min Range: -1.7966

Max Act: 1.1551. Min Act: -0.0000

Data Index: 573693 (C4 (Web Text))

Max Activating Token Index: 594

Text #10

Max Range: 1.7966. Min Range: -1.7966

Max Act: 1.1246. Min Act: -0.0000

Data Index: 175301 (C4 (Web Text))

Max Activating Token Index: 840

Text #11

Max Range: 1.7966. Min Range: -1.7966

Max Act: 1.1192. Min Act: -0.0000

Data Index: 132871 (C4 (Web Text))

Max Activating Token Index: 483

Text #12

Max Range: 1.7966. Min Range: -1.7966

Max Act: 1.1061. Min Act: -0.0000

Data Index: 942887 (C4 (Web Text))

Max Activating Token Index: 234

Text #13

Max Range: 1.7966. Min Range: -1.7966

Max Act: 1.1081. Min Act: 0.0000

Data Index: 767324 (C4 (Web Text))

Max Activating Token Index: 203

Text #14

Max Range: 1.7966. Min Range: -1.7966

Max Act: 1.1537. Min Act: -0.0000

Data Index: 269732 (C4 (Web Text))

Max Activating Token Index: 981

Text #15

Max Range: 1.7966. Min Range: -1.7966

Max Act: 1.0528. Min Act: -0.0000

Data Index: 1340417 (C4 (Web Text))

Max Activating Token Index: 836

Text #16

Max Range: 1.7966. Min Range: -1.7966

Max Act: 1.0409. Min Act: -0.0000

Data Index: 473424 (C4 (Web Text))

Max Activating Token Index: 134

Text #17

Max Range: 1.7966. Min Range: -1.7966

Max Act: 1.0330. Min Act: -0.0000

Data Index: 618585 (C4 (Web Text))

Max Activating Token Index: 579

Text #18

Max Range: 1.7966. Min Range: -1.7966

Max Act: 1.0115. Min Act: -0.0000

Data Index: 548247 (C4 (Web Text))

Max Activating Token Index: 682

Text #19

Max Range: 1.7966. Min Range: -1.7966

Max Act: 1.0034. Min Act: 0.0000

Data Index: 1121514 (C4 (Web Text))

Max Activating Token Index: 1002