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

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

Neuron 859 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: 2.1239. Min Range: -2.1239

Max Act: 2.1239. Min Act: -0.0000

Data Index: 1199053 (C4 (Web Text))

Max Activating Token Index: 128

Text #1

Max Range: 2.1239. Min Range: -2.1239

Max Act: 1.0036. Min Act: -0.0000

Data Index: 573788 (C4 (Web Text))

Max Activating Token Index: 680

Text #2

Max Range: 2.1239. Min Range: -2.1239

Max Act: 0.7789. Min Act: -0.0000

Data Index: 827780 (C4 (Web Text))

Max Activating Token Index: 401

Text #3

Max Range: 2.1239. Min Range: -2.1239

Max Act: 0.7514. Min Act: -0.0000

Data Index: 335981 (C4 (Web Text))

Max Activating Token Index: 1018

Text #4

Max Range: 2.1239. Min Range: -2.1239

Max Act: 0.7611. Min Act: -0.0000

Data Index: 527780 (C4 (Web Text))

Max Activating Token Index: 309

Text #5

Max Range: 2.1239. Min Range: -2.1239

Max Act: 0.7313. Min Act: -0.0000

Data Index: 1358609 (C4 (Web Text))

Max Activating Token Index: 879

Text #6

Max Range: 2.1239. Min Range: -2.1239

Max Act: 0.7060. Min Act: -0.0000

Data Index: 732503 (C4 (Web Text))

Max Activating Token Index: 955

Text #7

Max Range: 2.1239. Min Range: -2.1239

Max Act: 0.6609. Min Act: -0.0000

Data Index: 1091030 (C4 (Web Text))

Max Activating Token Index: 435

Text #8

Max Range: 2.1239. Min Range: -2.1239

Max Act: 0.5826. Min Act: -0.0000

Data Index: 329925 (C4 (Web Text))

Max Activating Token Index: 743

Text #9

Max Range: 2.1239. Min Range: -2.1239

Max Act: 0.5814. Min Act: -0.0000

Data Index: 439284 (C4 (Web Text))

Max Activating Token Index: 765

Text #10

Max Range: 2.1239. Min Range: -2.1239

Max Act: 0.5874. Min Act: -0.0000

Data Index: 99263 (C4 (Web Text))

Max Activating Token Index: 250

Text #11

Max Range: 2.1239. Min Range: -2.1239

Max Act: 0.5773. Min Act: -0.0000

Data Index: 424786 (C4 (Web Text))

Max Activating Token Index: 465

Text #12

Max Range: 2.1239. Min Range: -2.1239

Max Act: 0.5308. Min Act: -0.0000

Data Index: 237229 (C4 (Web Text))

Max Activating Token Index: 130

Text #13

Max Range: 2.1239. Min Range: -2.1239

Max Act: 0.5222. Min Act: -0.0000

Data Index: 470518 (C4 (Web Text))

Max Activating Token Index: 696

Text #14

Max Range: 2.1239. Min Range: -2.1239

Max Act: 0.5336. Min Act: -0.0000

Data Index: 732792 (C4 (Web Text))

Max Activating Token Index: 214

Text #15

Max Range: 2.1239. Min Range: -2.1239

Max Act: 0.5247. Min Act: -0.0000

Data Index: 667025 (C4 (Web Text))

Max Activating Token Index: 553

Text #16

Max Range: 2.1239. Min Range: -2.1239

Max Act: 0.5083. Min Act: -0.0000

Data Index: 1337248 (C4 (Web Text))

Max Activating Token Index: 217

Text #17

Max Range: 2.1239. Min Range: -2.1239

Max Act: 0.5160. Min Act: -0.0000

Data Index: 455923 (C4 (Web Text))

Max Activating Token Index: 263

Text #18

Max Range: 2.1239. Min Range: -2.1239

Max Act: 0.5106. Min Act: -0.0000

Data Index: 777566 (C4 (Web Text))

Max Activating Token Index: 69

Text #19

Max Range: 2.1239. Min Range: -2.1239

Max Act: 0.5643. Min Act: -0.0000

Data Index: 1051047 (C4 (Web Text))

Max Activating Token Index: 546