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

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

Neuron 3484 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1774. Min Act: -0.0001

Data Index: 1425900 (Python Code)

Max Activating Token Index: 573

Text #1

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1368. Min Act: -0.0001

Data Index: 860683 (C4 (Web Text))

Max Activating Token Index: 623

Text #2

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1201. Min Act: -0.0001

Data Index: 1273492 (C4 (Web Text))

Max Activating Token Index: 890

Text #3

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1181. Min Act: -0.0001

Data Index: 927417 (C4 (Web Text))

Max Activating Token Index: 535

Text #4

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1113. Min Act: -0.0001

Data Index: 81712 (C4 (Web Text))

Max Activating Token Index: 973

Text #5

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1064. Min Act: -0.0001

Data Index: 959376 (C4 (Web Text))

Max Activating Token Index: 858

Text #6

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1037. Min Act: -0.0001

Data Index: 418320 (C4 (Web Text))

Max Activating Token Index: 643

Text #7

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.0923. Min Act: -0.0001

Data Index: 1615903 (Python Code)

Max Activating Token Index: 380

Text #8

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1029. Min Act: -0.0001

Data Index: 281966 (C4 (Web Text))

Max Activating Token Index: 203

Text #9

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1024. Min Act: -0.0001

Data Index: 400503 (C4 (Web Text))

Max Activating Token Index: 547

Text #10

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1019. Min Act: -0.0001

Data Index: 547814 (C4 (Web Text))

Max Activating Token Index: 511

Text #11

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1021. Min Act: -0.0001

Data Index: 1204388 (C4 (Web Text))

Max Activating Token Index: 982

Text #12

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.0923. Min Act: -0.0001

Data Index: 396375 (C4 (Web Text))

Max Activating Token Index: 222

Text #13

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1035. Min Act: -0.0001

Data Index: 1614187 (Python Code)

Max Activating Token Index: 232

Text #14

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.0956. Min Act: -0.0001

Data Index: 1462369 (Python Code)

Max Activating Token Index: 380

Text #15

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.0979. Min Act: -0.0001

Data Index: 816119 (C4 (Web Text))

Max Activating Token Index: 782

Text #16

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.0976. Min Act: -0.0001

Data Index: 1082285 (C4 (Web Text))

Max Activating Token Index: 967

Text #17

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.0998. Min Act: -0.0001

Data Index: 1253238 (C4 (Web Text))

Max Activating Token Index: 477

Text #18

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.0882. Min Act: -0.0001

Data Index: 1588050 (Python Code)

Max Activating Token Index: 679

Text #19

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.0975. Min Act: -0.0001

Data Index: 1454399 (Python Code)

Max Activating Token Index: 662