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

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

Neuron 4130 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2138. Min Range: -3.2138

Max Act: 3.2138. Min Act: -0.0000

Data Index: 335291 (C4 (Web Text))

Max Activating Token Index: 586

Text #1

Max Range: 3.2138. Min Range: -3.2138

Max Act: 3.1925. Min Act: -0.0000

Data Index: 1094093 (C4 (Web Text))

Max Activating Token Index: 662

Text #2

Max Range: 3.2138. Min Range: -3.2138

Max Act: 3.0249. Min Act: -0.0000

Data Index: 799568 (C4 (Web Text))

Max Activating Token Index: 494

Text #3

Max Range: 3.2138. Min Range: -3.2138

Max Act: 2.9438. Min Act: -0.0000

Data Index: 1117408 (C4 (Web Text))

Max Activating Token Index: 179

Text #4

Max Range: 3.2138. Min Range: -3.2138

Max Act: 2.9160. Min Act: -0.0000

Data Index: 998143 (C4 (Web Text))

Max Activating Token Index: 746

Text #5

Max Range: 3.2138. Min Range: -3.2138

Max Act: 3.1937. Min Act: -0.0000

Data Index: 277709 (C4 (Web Text))

Max Activating Token Index: 315

Text #6

Max Range: 3.2138. Min Range: -3.2138

Max Act: 3.0575. Min Act: -0.0000

Data Index: 213369 (C4 (Web Text))

Max Activating Token Index: 757

Text #7

Max Range: 3.2138. Min Range: -3.2138

Max Act: 3.1815. Min Act: -0.0000

Data Index: 378825 (C4 (Web Text))

Max Activating Token Index: 749

Text #8

Max Range: 3.2138. Min Range: -3.2138

Max Act: 3.0166. Min Act: -0.0000

Data Index: 1080773 (C4 (Web Text))

Max Activating Token Index: 537

Text #9

Max Range: 3.2138. Min Range: -3.2138

Max Act: 2.9254. Min Act: -0.0000

Data Index: 690265 (C4 (Web Text))

Max Activating Token Index: 208

Text #10

Max Range: 3.2138. Min Range: -3.2138

Max Act: 2.9350. Min Act: -0.0000

Data Index: 397075 (C4 (Web Text))

Max Activating Token Index: 420

Text #11

Max Range: 3.2138. Min Range: -3.2138

Max Act: 2.7932. Min Act: -0.0000

Data Index: 570505 (C4 (Web Text))

Max Activating Token Index: 162

Text #12

Max Range: 3.2138. Min Range: -3.2138

Max Act: 2.7714. Min Act: -0.0000

Data Index: 322026 (C4 (Web Text))

Max Activating Token Index: 107

Text #13

Max Range: 3.2138. Min Range: -3.2138

Max Act: 2.7552. Min Act: -0.0000

Data Index: 484414 (C4 (Web Text))

Max Activating Token Index: 535

Text #14

Max Range: 3.2138. Min Range: -3.2138

Max Act: 2.7581. Min Act: -0.0000

Data Index: 1287668 (C4 (Web Text))

Max Activating Token Index: 657

Text #15

Max Range: 3.2138. Min Range: -3.2138

Max Act: 2.8935. Min Act: -0.0000

Data Index: 946006 (C4 (Web Text))

Max Activating Token Index: 464

Text #16

Max Range: 3.2138. Min Range: -3.2138

Max Act: 3.0233. Min Act: -0.0000

Data Index: 910861 (C4 (Web Text))

Max Activating Token Index: 377

Text #17

Max Range: 3.2138. Min Range: -3.2138

Max Act: 2.6929. Min Act: -0.0000

Data Index: 36898 (C4 (Web Text))

Max Activating Token Index: 952

Text #18

Max Range: 3.2138. Min Range: -3.2138

Max Act: 2.8222. Min Act: -0.0000

Data Index: 1203021 (C4 (Web Text))

Max Activating Token Index: 746

Text #19

Max Range: 3.2138. Min Range: -3.2138

Max Act: 2.7962. Min Act: -0.0000

Data Index: 114896 (C4 (Web Text))

Max Activating Token Index: 891