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

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

Neuron 219 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.1231. Min Act: -0.0001

Data Index: 1527382 (Python Code)

Max Activating Token Index: 897

Text #1

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.1200. Min Act: -0.0001

Data Index: 1387750 (Python Code)

Max Activating Token Index: 862

Text #2

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.1088. Min Act: -0.0000

Data Index: 664762 (C4 (Web Text))

Max Activating Token Index: 758

Text #3

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.1109. Min Act: -0.0001

Data Index: 1585974 (Python Code)

Max Activating Token Index: 482

Text #4

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.1094. Min Act: -0.0001

Data Index: 1623507 (Python Code)

Max Activating Token Index: 156

Text #5

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.1029. Min Act: -0.0000

Data Index: 270178 (C4 (Web Text))

Max Activating Token Index: 144

Text #6

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.1037. Min Act: -0.0000

Data Index: 509047 (C4 (Web Text))

Max Activating Token Index: 125

Text #7

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.1064. Min Act: -0.0001

Data Index: 1393650 (Python Code)

Max Activating Token Index: 734

Text #8

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.0986. Min Act: -0.0001

Data Index: 799365 (C4 (Web Text))

Max Activating Token Index: 885

Text #9

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.0999. Min Act: -0.0000

Data Index: 1051521 (C4 (Web Text))

Max Activating Token Index: 306

Text #10

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.0985. Min Act: -0.0001

Data Index: 1504679 (Python Code)

Max Activating Token Index: 757

Text #11

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.0989. Min Act: -0.0000

Data Index: 1390644 (Python Code)

Max Activating Token Index: 114

Text #12

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.0992. Min Act: -0.0000

Data Index: 660550 (C4 (Web Text))

Max Activating Token Index: 419

Text #13

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.0984. Min Act: -0.0001

Data Index: 1552083 (Python Code)

Max Activating Token Index: 890

Text #14

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.0934. Min Act: -0.0000

Data Index: 1501188 (Python Code)

Max Activating Token Index: 478

Text #15

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.0965. Min Act: -0.0001

Data Index: 1375200 (Python Code)

Max Activating Token Index: 1019

Text #16

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.0919. Min Act: -0.0000

Data Index: 805641 (C4 (Web Text))

Max Activating Token Index: 65

Text #17

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.0995. Min Act: -0.0001

Data Index: 761482 (C4 (Web Text))

Max Activating Token Index: 315

Text #18

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.0920. Min Act: -0.0001

Data Index: 1568915 (Python Code)

Max Activating Token Index: 138

Text #19

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.0950. Min Act: -0.0001

Data Index: 1442428 (Python Code)

Max Activating Token Index: 904