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

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

Neuron 4243 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2162. Min Range: -1.2162

Max Act: 1.2162. Min Act: -0.0000

Data Index: 454783 (C4 (Web Text))

Max Activating Token Index: 760

Text #1

Max Range: 1.2162. Min Range: -1.2162

Max Act: 0.9242. Min Act: -0.0000

Data Index: 41449 (C4 (Web Text))

Max Activating Token Index: 465

Text #2

Max Range: 1.2162. Min Range: -1.2162

Max Act: 0.9123. Min Act: -0.0000

Data Index: 1184268 (C4 (Web Text))

Max Activating Token Index: 383

Text #3

Max Range: 1.2162. Min Range: -1.2162

Max Act: 0.8851. Min Act: -0.0000

Data Index: 1212308 (C4 (Web Text))

Max Activating Token Index: 122

Text #4

Max Range: 1.2162. Min Range: -1.2162

Max Act: 0.7706. Min Act: -0.0000

Data Index: 527515 (C4 (Web Text))

Max Activating Token Index: 830

Text #5

Max Range: 1.2162. Min Range: -1.2162

Max Act: 0.8116. Min Act: 0.0000

Data Index: 1057590 (C4 (Web Text))

Max Activating Token Index: 647

Text #6

Max Range: 1.2162. Min Range: -1.2162

Max Act: 0.7475. Min Act: -0.0000

Data Index: 1346059 (C4 (Web Text))

Max Activating Token Index: 476

Text #7

Max Range: 1.2162. Min Range: -1.2162

Max Act: 0.7977. Min Act: -0.0000

Data Index: 1027239 (C4 (Web Text))

Max Activating Token Index: 298

Text #8

Max Range: 1.2162. Min Range: -1.2162

Max Act: 0.7604. Min Act: -0.0000

Data Index: 487099 (C4 (Web Text))

Max Activating Token Index: 948

Text #9

Max Range: 1.2162. Min Range: -1.2162

Max Act: 0.7563. Min Act: -0.0000

Data Index: 577466 (C4 (Web Text))

Max Activating Token Index: 112

Text #10

Max Range: 1.2162. Min Range: -1.2162

Max Act: 0.7442. Min Act: -0.0000

Data Index: 818898 (C4 (Web Text))

Max Activating Token Index: 476

Text #11

Max Range: 1.2162. Min Range: -1.2162

Max Act: 0.7319. Min Act: -0.0000

Data Index: 154948 (C4 (Web Text))

Max Activating Token Index: 530

Text #12

Max Range: 1.2162. Min Range: -1.2162

Max Act: 0.7509. Min Act: -0.0000

Data Index: 89441 (C4 (Web Text))

Max Activating Token Index: 32

Text #13

Max Range: 1.2162. Min Range: -1.2162

Max Act: 0.7232. Min Act: -0.0000

Data Index: 376253 (C4 (Web Text))

Max Activating Token Index: 952

Text #14

Max Range: 1.2162. Min Range: -1.2162

Max Act: 0.7001. Min Act: -0.0000

Data Index: 810699 (C4 (Web Text))

Max Activating Token Index: 888

Text #15

Max Range: 1.2162. Min Range: -1.2162

Max Act: 0.7175. Min Act: -0.0000

Data Index: 16862 (C4 (Web Text))

Max Activating Token Index: 329

Text #16

Max Range: 1.2162. Min Range: -1.2162

Max Act: 0.7110. Min Act: -0.0000

Data Index: 1170258 (C4 (Web Text))

Max Activating Token Index: 46

Text #17

Max Range: 1.2162. Min Range: -1.2162

Max Act: 0.7332. Min Act: -0.0000

Data Index: 1236163 (C4 (Web Text))

Max Activating Token Index: 541

Text #18

Max Range: 1.2162. Min Range: -1.2162

Max Act: 0.7226. Min Act: -0.0000

Data Index: 942795 (C4 (Web Text))

Max Activating Token Index: 156

Text #19

Max Range: 1.2162. Min Range: -1.2162

Max Act: 0.7055. Min Act: -0.0000

Data Index: 58316 (C4 (Web Text))

Max Activating Token Index: 994