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

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

Neuron 2844 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: 1.9850. Min Range: -1.9850

Max Act: 1.8913. Min Act: -0.0000

Data Index: 767313 (C4 (Web Text))

Max Activating Token Index: 801

Text #1

Max Range: 1.9850. Min Range: -1.9850

Max Act: 1.9850. Min Act: -0.0000

Data Index: 849542 (C4 (Web Text))

Max Activating Token Index: 938

Text #2

Max Range: 1.9850. Min Range: -1.9850

Max Act: 1.8875. Min Act: -0.0000

Data Index: 474143 (C4 (Web Text))

Max Activating Token Index: 452

Text #3

Max Range: 1.9850. Min Range: -1.9850

Max Act: 1.7443. Min Act: -0.0000

Data Index: 645647 (C4 (Web Text))

Max Activating Token Index: 743

Text #4

Max Range: 1.9850. Min Range: -1.9850

Max Act: 1.4758. Min Act: -0.0000

Data Index: 1148777 (C4 (Web Text))

Max Activating Token Index: 87

Text #5

Max Range: 1.9850. Min Range: -1.9850

Max Act: 1.5116. Min Act: -0.0000

Data Index: 1046257 (C4 (Web Text))

Max Activating Token Index: 122

Text #6

Max Range: 1.9850. Min Range: -1.9850

Max Act: 1.4990. Min Act: -0.0000

Data Index: 865657 (C4 (Web Text))

Max Activating Token Index: 284

Text #7

Max Range: 1.9850. Min Range: -1.9850

Max Act: 1.4050. Min Act: -0.0000

Data Index: 1049452 (C4 (Web Text))

Max Activating Token Index: 857

Text #8

Max Range: 1.9850. Min Range: -1.9850

Max Act: 1.4218. Min Act: -0.0000

Data Index: 189862 (C4 (Web Text))

Max Activating Token Index: 901

Text #9

Max Range: 1.9850. Min Range: -1.9850

Max Act: 1.4165. Min Act: -0.0000

Data Index: 550724 (C4 (Web Text))

Max Activating Token Index: 26

Text #10

Max Range: 1.9850. Min Range: -1.9850

Max Act: 1.2355. Min Act: -0.0000

Data Index: 25040 (C4 (Web Text))

Max Activating Token Index: 56

Text #11

Max Range: 1.9850. Min Range: -1.9850

Max Act: 1.4618. Min Act: -0.0000

Data Index: 117504 (C4 (Web Text))

Max Activating Token Index: 864

Text #12

Max Range: 1.9850. Min Range: -1.9850

Max Act: 1.3499. Min Act: -0.0000

Data Index: 635772 (C4 (Web Text))

Max Activating Token Index: 169

Text #13

Max Range: 1.9850. Min Range: -1.9850

Max Act: 1.3074. Min Act: -0.0000

Data Index: 494842 (C4 (Web Text))

Max Activating Token Index: 806

Text #14

Max Range: 1.9850. Min Range: -1.9850

Max Act: 1.2924. Min Act: -0.0000

Data Index: 805777 (C4 (Web Text))

Max Activating Token Index: 893

Text #15

Max Range: 1.9850. Min Range: -1.9850

Max Act: 1.2613. Min Act: -0.0000

Data Index: 1156954 (C4 (Web Text))

Max Activating Token Index: 819

Text #16

Max Range: 1.9850. Min Range: -1.9850

Max Act: 1.1777. Min Act: -0.0000

Data Index: 1156239 (C4 (Web Text))

Max Activating Token Index: 682

Text #17

Max Range: 1.9850. Min Range: -1.9850

Max Act: 1.3150. Min Act: -0.0000

Data Index: 369683 (C4 (Web Text))

Max Activating Token Index: 861

Text #18

Max Range: 1.9850. Min Range: -1.9850

Max Act: 1.2409. Min Act: -0.0000

Data Index: 640832 (C4 (Web Text))

Max Activating Token Index: 847

Text #19

Max Range: 1.9850. Min Range: -1.9850

Max Act: 1.2083. Min Act: -0.0000

Data Index: 1357407 (C4 (Web Text))

Max Activating Token Index: 386