Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2261 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.5725. Min Act: -0.0001

Data Index: 1157878 (C4 (Web Text))

Max Activating Token Index: 894

Text #1

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.5660. Min Act: -0.0001

Data Index: 154314 (C4 (Web Text))

Max Activating Token Index: 301

Text #2

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.5358. Min Act: -0.0001

Data Index: 743841 (C4 (Web Text))

Max Activating Token Index: 645

Text #3

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.5066. Min Act: -0.0001

Data Index: 1096413 (C4 (Web Text))

Max Activating Token Index: 893

Text #4

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.5296. Min Act: -0.0002

Data Index: 874451 (C4 (Web Text))

Max Activating Token Index: 231

Text #5

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.4937. Min Act: -0.0001

Data Index: 1015754 (C4 (Web Text))

Max Activating Token Index: 666

Text #6

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.5084. Min Act: -0.0002

Data Index: 110426 (C4 (Web Text))

Max Activating Token Index: 911

Text #7

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.5190. Min Act: -0.0002

Data Index: 483570 (C4 (Web Text))

Max Activating Token Index: 603

Text #8

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.4987. Min Act: -0.0002

Data Index: 852125 (C4 (Web Text))

Max Activating Token Index: 596

Text #9

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.5081. Min Act: -0.0002

Data Index: 24265 (C4 (Web Text))

Max Activating Token Index: 811

Text #10

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.5242. Min Act: -0.0002

Data Index: 832440 (C4 (Web Text))

Max Activating Token Index: 928

Text #11

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.4743. Min Act: -0.0002

Data Index: 664365 (C4 (Web Text))

Max Activating Token Index: 323

Text #12

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.5227. Min Act: -0.0001

Data Index: 1213388 (C4 (Web Text))

Max Activating Token Index: 263

Text #13

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.5122. Min Act: -0.0001

Data Index: 1053084 (C4 (Web Text))

Max Activating Token Index: 960

Text #14

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.5150. Min Act: -0.0002

Data Index: 358726 (C4 (Web Text))

Max Activating Token Index: 957

Text #15

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.5028. Min Act: -0.0001

Data Index: 634480 (C4 (Web Text))

Max Activating Token Index: 912

Text #16

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.5035. Min Act: -0.0002

Data Index: 632981 (C4 (Web Text))

Max Activating Token Index: 822

Text #17

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.4842. Min Act: -0.0002

Data Index: 893295 (C4 (Web Text))

Max Activating Token Index: 736

Text #18

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.5003. Min Act: -0.0002

Data Index: 829484 (C4 (Web Text))

Max Activating Token Index: 849

Text #19

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.4784. Min Act: -0.0001

Data Index: 1064970 (C4 (Web Text))

Max Activating Token Index: 691