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

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

Neuron 5036 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.8085. Min Act: -0.0000

Data Index: 284673 (C4 (Web Text))

Max Activating Token Index: 927

Text #1

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.7649. Min Act: -0.0000

Data Index: 949683 (C4 (Web Text))

Max Activating Token Index: 470

Text #2

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.7274. Min Act: -0.0000

Data Index: 1143652 (C4 (Web Text))

Max Activating Token Index: 512

Text #3

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.7265. Min Act: -0.0000

Data Index: 470745 (C4 (Web Text))

Max Activating Token Index: 701

Text #4

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.7627. Min Act: -0.0000

Data Index: 102813 (C4 (Web Text))

Max Activating Token Index: 21

Text #5

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.7375. Min Act: -0.0000

Data Index: 519795 (C4 (Web Text))

Max Activating Token Index: 207

Text #6

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.7063. Min Act: -0.0000

Data Index: 791593 (C4 (Web Text))

Max Activating Token Index: 894

Text #7

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.7023. Min Act: -0.0000

Data Index: 980304 (C4 (Web Text))

Max Activating Token Index: 301

Text #8

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.7147. Min Act: -0.0000

Data Index: 1258017 (C4 (Web Text))

Max Activating Token Index: 689

Text #9

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.6673. Min Act: -0.0000

Data Index: 356708 (C4 (Web Text))

Max Activating Token Index: 711

Text #10

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.7296. Min Act: -0.0000

Data Index: 408511 (C4 (Web Text))

Max Activating Token Index: 699

Text #11

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.6997. Min Act: -0.0000

Data Index: 595617 (C4 (Web Text))

Max Activating Token Index: 33

Text #12

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.6973. Min Act: -0.0000

Data Index: 265394 (C4 (Web Text))

Max Activating Token Index: 181

Text #13

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.6974. Min Act: -0.0000

Data Index: 1250567 (C4 (Web Text))

Max Activating Token Index: 191

Text #14

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.6858. Min Act: -0.0000

Data Index: 1227584 (C4 (Web Text))

Max Activating Token Index: 767

Text #15

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.6846. Min Act: -0.0000

Data Index: 793420 (C4 (Web Text))

Max Activating Token Index: 426

Text #16

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.6603. Min Act: -0.0000

Data Index: 943839 (C4 (Web Text))

Max Activating Token Index: 873

Text #17

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.6948. Min Act: -0.0000

Data Index: 562129 (C4 (Web Text))

Max Activating Token Index: 713

Text #18

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.6732. Min Act: -0.0000

Data Index: 592661 (C4 (Web Text))

Max Activating Token Index: 359

Text #19

Max Range: 0.8085. Min Range: -0.8085

Max Act: 0.6673. Min Act: -0.0000

Data Index: 194176 (C4 (Web Text))

Max Activating Token Index: 750