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

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

Neuron 3248 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: 0.6825. Min Range: -0.6825

Max Act: 0.6812. Min Act: -0.0002

Data Index: 483255 (C4 (Web Text))

Max Activating Token Index: 698

Text #1

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.6825. Min Act: -0.0001

Data Index: 1005005 (C4 (Web Text))

Max Activating Token Index: 442

Text #2

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.6483. Min Act: -0.0002

Data Index: 643097 (C4 (Web Text))

Max Activating Token Index: 828

Text #3

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.6079. Min Act: -0.0001

Data Index: 1137356 (C4 (Web Text))

Max Activating Token Index: 266

Text #4

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.6156. Min Act: -0.0001

Data Index: 1334043 (C4 (Web Text))

Max Activating Token Index: 865

Text #5

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.5949. Min Act: -0.0002

Data Index: 666662 (C4 (Web Text))

Max Activating Token Index: 401

Text #6

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.5871. Min Act: -0.0001

Data Index: 987426 (C4 (Web Text))

Max Activating Token Index: 449

Text #7

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.5393. Min Act: -0.0002

Data Index: 782105 (C4 (Web Text))

Max Activating Token Index: 467

Text #8

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.5462. Min Act: -0.0001

Data Index: 713396 (C4 (Web Text))

Max Activating Token Index: 306

Text #9

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.5893. Min Act: -0.0002

Data Index: 692947 (C4 (Web Text))

Max Activating Token Index: 973

Text #10

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.5717. Min Act: -0.0001

Data Index: 625419 (C4 (Web Text))

Max Activating Token Index: 891

Text #11

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.5240. Min Act: -0.0001

Data Index: 40639 (C4 (Web Text))

Max Activating Token Index: 49

Text #12

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.5379. Min Act: -0.0002

Data Index: 529368 (C4 (Web Text))

Max Activating Token Index: 119

Text #13

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.5342. Min Act: -0.0002

Data Index: 960780 (C4 (Web Text))

Max Activating Token Index: 537

Text #14

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.4995. Min Act: -0.0002

Data Index: 1148788 (C4 (Web Text))

Max Activating Token Index: 854

Text #15

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.5096. Min Act: -0.0001

Data Index: 1224155 (C4 (Web Text))

Max Activating Token Index: 855

Text #16

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.4820. Min Act: -0.0002

Data Index: 1036940 (C4 (Web Text))

Max Activating Token Index: 784

Text #17

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.4838. Min Act: -0.0001

Data Index: 283008 (C4 (Web Text))

Max Activating Token Index: 531

Text #18

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.4913. Min Act: -0.0002

Data Index: 41875 (C4 (Web Text))

Max Activating Token Index: 278

Text #19

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.4901. Min Act: -0.0002

Data Index: 148515 (C4 (Web Text))

Max Activating Token Index: 401