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

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

Neuron 1434 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5767. Min Range: -1.5767

Max Act: 1.5099. Min Act: -0.0002

Data Index: 707073 (C4 (Web Text))

Max Activating Token Index: 959

Text #1

Max Range: 1.5767. Min Range: -1.5767

Max Act: 1.5767. Min Act: -0.0002

Data Index: 1110669 (C4 (Web Text))

Max Activating Token Index: 824

Text #2

Max Range: 1.5767. Min Range: -1.5767

Max Act: 1.5124. Min Act: -0.0002

Data Index: 1167235 (C4 (Web Text))

Max Activating Token Index: 259

Text #3

Max Range: 1.5767. Min Range: -1.5767

Max Act: 1.3887. Min Act: -0.0002

Data Index: 62084 (C4 (Web Text))

Max Activating Token Index: 241

Text #4

Max Range: 1.5767. Min Range: -1.5767

Max Act: 1.4727. Min Act: -0.0002

Data Index: 772172 (C4 (Web Text))

Max Activating Token Index: 79

Text #5

Max Range: 1.5767. Min Range: -1.5767

Max Act: 1.4729. Min Act: -0.0002

Data Index: 841419 (C4 (Web Text))

Max Activating Token Index: 417

Text #6

Max Range: 1.5767. Min Range: -1.5767

Max Act: 1.2976. Min Act: -0.0002

Data Index: 1243451 (C4 (Web Text))

Max Activating Token Index: 357

Text #7

Max Range: 1.5767. Min Range: -1.5767

Max Act: 1.3372. Min Act: -0.0002

Data Index: 1298283 (C4 (Web Text))

Max Activating Token Index: 255

Text #8

Max Range: 1.5767. Min Range: -1.5767

Max Act: 1.3798. Min Act: -0.0002

Data Index: 1107981 (C4 (Web Text))

Max Activating Token Index: 927

Text #9

Max Range: 1.5767. Min Range: -1.5767

Max Act: 1.3094. Min Act: -0.0002

Data Index: 36284 (C4 (Web Text))

Max Activating Token Index: 913

Text #10

Max Range: 1.5767. Min Range: -1.5767

Max Act: 1.2019. Min Act: -0.0002

Data Index: 1038269 (C4 (Web Text))

Max Activating Token Index: 864

Text #11

Max Range: 1.5767. Min Range: -1.5767

Max Act: 1.4071. Min Act: -0.0002

Data Index: 718307 (C4 (Web Text))

Max Activating Token Index: 243

Text #12

Max Range: 1.5767. Min Range: -1.5767

Max Act: 1.1860. Min Act: -0.0002

Data Index: 1059309 (C4 (Web Text))

Max Activating Token Index: 674

Text #13

Max Range: 1.5767. Min Range: -1.5767

Max Act: 1.3375. Min Act: -0.0002

Data Index: 1178047 (C4 (Web Text))

Max Activating Token Index: 804

Text #14

Max Range: 1.5767. Min Range: -1.5767

Max Act: 1.5442. Min Act: -0.0002

Data Index: 584838 (C4 (Web Text))

Max Activating Token Index: 327

Text #15

Max Range: 1.5767. Min Range: -1.5767

Max Act: 1.2489. Min Act: -0.0002

Data Index: 934730 (C4 (Web Text))

Max Activating Token Index: 919

Text #16

Max Range: 1.5767. Min Range: -1.5767

Max Act: 1.1116. Min Act: -0.0002

Data Index: 13276 (C4 (Web Text))

Max Activating Token Index: 865

Text #17

Max Range: 1.5767. Min Range: -1.5767

Max Act: 1.3223. Min Act: -0.0002

Data Index: 639187 (C4 (Web Text))

Max Activating Token Index: 612

Text #18

Max Range: 1.5767. Min Range: -1.5767

Max Act: 1.2950. Min Act: -0.0002

Data Index: 579149 (C4 (Web Text))

Max Activating Token Index: 965

Text #19

Max Range: 1.5767. Min Range: -1.5767

Max Act: 1.1892. Min Act: -0.0002

Data Index: 38264 (C4 (Web Text))

Max Activating Token Index: 312