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

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

Neuron 1690 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2710. Min Range: -2.2710

Max Act: 2.2710. Min Act: -0.0000

Data Index: 1064126 (C4 (Web Text))

Max Activating Token Index: 216

Text #1

Max Range: 2.2710. Min Range: -2.2710

Max Act: 2.1158. Min Act: -0.0000

Data Index: 1266347 (C4 (Web Text))

Max Activating Token Index: 544

Text #2

Max Range: 2.2710. Min Range: -2.2710

Max Act: 1.9652. Min Act: -0.0000

Data Index: 1047215 (C4 (Web Text))

Max Activating Token Index: 1009

Text #3

Max Range: 2.2710. Min Range: -2.2710

Max Act: 2.0728. Min Act: -0.0000

Data Index: 481886 (C4 (Web Text))

Max Activating Token Index: 899

Text #4

Max Range: 2.2710. Min Range: -2.2710

Max Act: 2.0446. Min Act: -0.0000

Data Index: 1272225 (C4 (Web Text))

Max Activating Token Index: 552

Text #5

Max Range: 2.2710. Min Range: -2.2710

Max Act: 2.0519. Min Act: -0.0000

Data Index: 1079531 (C4 (Web Text))

Max Activating Token Index: 662

Text #6

Max Range: 2.2710. Min Range: -2.2710

Max Act: 1.9421. Min Act: -0.0000

Data Index: 222640 (C4 (Web Text))

Max Activating Token Index: 968

Text #7

Max Range: 2.2710. Min Range: -2.2710

Max Act: 1.8815. Min Act: -0.0000

Data Index: 493015 (C4 (Web Text))

Max Activating Token Index: 943

Text #8

Max Range: 2.2710. Min Range: -2.2710

Max Act: 1.8662. Min Act: -0.0000

Data Index: 803539 (C4 (Web Text))

Max Activating Token Index: 946

Text #9

Max Range: 2.2710. Min Range: -2.2710

Max Act: 1.9664. Min Act: -0.0000

Data Index: 807539 (C4 (Web Text))

Max Activating Token Index: 590

Text #10

Max Range: 2.2710. Min Range: -2.2710

Max Act: 1.8622. Min Act: -0.0000

Data Index: 325831 (C4 (Web Text))

Max Activating Token Index: 917

Text #11

Max Range: 2.2710. Min Range: -2.2710

Max Act: 1.7345. Min Act: -0.0000

Data Index: 722200 (C4 (Web Text))

Max Activating Token Index: 687

Text #12

Max Range: 2.2710. Min Range: -2.2710

Max Act: 1.6222. Min Act: -0.0000

Data Index: 385850 (C4 (Web Text))

Max Activating Token Index: 789

Text #13

Max Range: 2.2710. Min Range: -2.2710

Max Act: 1.8237. Min Act: -0.0000

Data Index: 1146211 (C4 (Web Text))

Max Activating Token Index: 833

Text #14

Max Range: 2.2710. Min Range: -2.2710

Max Act: 1.6979. Min Act: -0.0000

Data Index: 639897 (C4 (Web Text))

Max Activating Token Index: 88

Text #15

Max Range: 2.2710. Min Range: -2.2710

Max Act: 1.7947. Min Act: -0.0000

Data Index: 408322 (C4 (Web Text))

Max Activating Token Index: 174

Text #16

Max Range: 2.2710. Min Range: -2.2710

Max Act: 1.8870. Min Act: -0.0000

Data Index: 1303916 (C4 (Web Text))

Max Activating Token Index: 564

Text #17

Max Range: 2.2710. Min Range: -2.2710

Max Act: 1.7727. Min Act: -0.0000

Data Index: 643064 (C4 (Web Text))

Max Activating Token Index: 330

Text #18

Max Range: 2.2710. Min Range: -2.2710

Max Act: 1.6850. Min Act: -0.0000

Data Index: 200217 (C4 (Web Text))

Max Activating Token Index: 839

Text #19

Max Range: 2.2710. Min Range: -2.2710

Max Act: 1.7595. Min Act: -0.0000

Data Index: 990243 (C4 (Web Text))

Max Activating Token Index: 581