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

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

Neuron 1070 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: 0.2163. Min Range: -0.2163

Max Act: 0.1781. Min Act: -0.0002

Data Index: 368286 (C4 (Web Text))

Max Activating Token Index: 294

Text #1

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.2068. Min Act: -0.0002

Data Index: 807029 (C4 (Web Text))

Max Activating Token Index: 979

Text #2

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1980. Min Act: -0.0002

Data Index: 671303 (C4 (Web Text))

Max Activating Token Index: 832

Text #3

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.2163. Min Act: -0.0002

Data Index: 1075096 (C4 (Web Text))

Max Activating Token Index: 859

Text #4

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.2004. Min Act: -0.0002

Data Index: 837220 (C4 (Web Text))

Max Activating Token Index: 613

Text #5

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.2050. Min Act: -0.0002

Data Index: 252815 (C4 (Web Text))

Max Activating Token Index: 528

Text #6

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.2022. Min Act: -0.0002

Data Index: 457143 (C4 (Web Text))

Max Activating Token Index: 1004

Text #7

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1993. Min Act: -0.0002

Data Index: 977504 (C4 (Web Text))

Max Activating Token Index: 426

Text #8

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1963. Min Act: -0.0002

Data Index: 209028 (C4 (Web Text))

Max Activating Token Index: 498

Text #9

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1945. Min Act: -0.0002

Data Index: 766454 (C4 (Web Text))

Max Activating Token Index: 677

Text #10

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1969. Min Act: -0.0002

Data Index: 898689 (C4 (Web Text))

Max Activating Token Index: 408

Text #11

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1873. Min Act: -0.0002

Data Index: 291961 (C4 (Web Text))

Max Activating Token Index: 575

Text #12

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.2013. Min Act: -0.0002

Data Index: 231645 (C4 (Web Text))

Max Activating Token Index: 922

Text #13

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1881. Min Act: -0.0002

Data Index: 208352 (C4 (Web Text))

Max Activating Token Index: 579

Text #14

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1825. Min Act: -0.0002

Data Index: 1160253 (C4 (Web Text))

Max Activating Token Index: 914

Text #15

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1853. Min Act: -0.0002

Data Index: 356060 (C4 (Web Text))

Max Activating Token Index: 697

Text #16

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1930. Min Act: -0.0002

Data Index: 410019 (C4 (Web Text))

Max Activating Token Index: 683

Text #17

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1867. Min Act: -0.0002

Data Index: 1336100 (C4 (Web Text))

Max Activating Token Index: 724

Text #18

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1929. Min Act: -0.0002

Data Index: 1348942 (C4 (Web Text))

Max Activating Token Index: 259

Text #19

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1748. Min Act: -0.0002

Data Index: 1187969 (C4 (Web Text))

Max Activating Token Index: 258