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

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

Neuron 3207 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1668. Min Range: -1.1668

Max Act: 1.1668. Min Act: -0.0000

Data Index: 1179668 (C4 (Web Text))

Max Activating Token Index: 839

Text #1

Max Range: 1.1668. Min Range: -1.1668

Max Act: 1.0238. Min Act: -0.0000

Data Index: 374640 (C4 (Web Text))

Max Activating Token Index: 835

Text #2

Max Range: 1.1668. Min Range: -1.1668

Max Act: 0.9844. Min Act: -0.0000

Data Index: 352093 (C4 (Web Text))

Max Activating Token Index: 166

Text #3

Max Range: 1.1668. Min Range: -1.1668

Max Act: 0.9900. Min Act: -0.0000

Data Index: 1204790 (C4 (Web Text))

Max Activating Token Index: 348

Text #4

Max Range: 1.1668. Min Range: -1.1668

Max Act: 0.9408. Min Act: -0.0000

Data Index: 332296 (C4 (Web Text))

Max Activating Token Index: 298

Text #5

Max Range: 1.1668. Min Range: -1.1668

Max Act: 0.9928. Min Act: -0.0000

Data Index: 970724 (C4 (Web Text))

Max Activating Token Index: 337

Text #6

Max Range: 1.1668. Min Range: -1.1668

Max Act: 0.8516. Min Act: -0.0000

Data Index: 779815 (C4 (Web Text))

Max Activating Token Index: 587

Text #7

Max Range: 1.1668. Min Range: -1.1668

Max Act: 0.8762. Min Act: -0.0000

Data Index: 400781 (C4 (Web Text))

Max Activating Token Index: 909

Text #8

Max Range: 1.1668. Min Range: -1.1668

Max Act: 0.8951. Min Act: -0.0000

Data Index: 707855 (C4 (Web Text))

Max Activating Token Index: 939

Text #9

Max Range: 1.1668. Min Range: -1.1668

Max Act: 0.8509. Min Act: -0.0000

Data Index: 1278834 (C4 (Web Text))

Max Activating Token Index: 565

Text #10

Max Range: 1.1668. Min Range: -1.1668

Max Act: 0.9559. Min Act: -0.0000

Data Index: 466524 (C4 (Web Text))

Max Activating Token Index: 170

Text #11

Max Range: 1.1668. Min Range: -1.1668

Max Act: 0.8073. Min Act: -0.0000

Data Index: 88582 (C4 (Web Text))

Max Activating Token Index: 770

Text #12

Max Range: 1.1668. Min Range: -1.1668

Max Act: 0.8426. Min Act: -0.0000

Data Index: 783294 (C4 (Web Text))

Max Activating Token Index: 565

Text #13

Max Range: 1.1668. Min Range: -1.1668

Max Act: 0.8591. Min Act: -0.0000

Data Index: 1195899 (C4 (Web Text))

Max Activating Token Index: 397

Text #14

Max Range: 1.1668. Min Range: -1.1668

Max Act: 0.8250. Min Act: -0.0000

Data Index: 373617 (C4 (Web Text))

Max Activating Token Index: 405

Text #15

Max Range: 1.1668. Min Range: -1.1668

Max Act: 0.8241. Min Act: -0.0000

Data Index: 504721 (C4 (Web Text))

Max Activating Token Index: 655

Text #16

Max Range: 1.1668. Min Range: -1.1668

Max Act: 0.8237. Min Act: -0.0000

Data Index: 1170463 (C4 (Web Text))

Max Activating Token Index: 904

Text #17

Max Range: 1.1668. Min Range: -1.1668

Max Act: 0.7921. Min Act: -0.0000

Data Index: 1211420 (C4 (Web Text))

Max Activating Token Index: 195

Text #18

Max Range: 1.1668. Min Range: -1.1668

Max Act: 0.7871. Min Act: -0.0000

Data Index: 1144362 (C4 (Web Text))

Max Activating Token Index: 145

Text #19

Max Range: 1.1668. Min Range: -1.1668

Max Act: 0.7807. Min Act: -0.0000

Data Index: 1084118 (C4 (Web Text))

Max Activating Token Index: 218