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

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

Neuron 2671 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4893. Min Range: -0.4893

Max Act: 0.4893. Min Act: -0.0001

Data Index: 238611 (C4 (Web Text))

Max Activating Token Index: 750

Text #1

Max Range: 0.4893. Min Range: -0.4893

Max Act: 0.4058. Min Act: -0.0001

Data Index: 1124869 (C4 (Web Text))

Max Activating Token Index: 78

Text #2

Max Range: 0.4893. Min Range: -0.4893

Max Act: 0.4113. Min Act: -0.0001

Data Index: 1210078 (C4 (Web Text))

Max Activating Token Index: 359

Text #3

Max Range: 0.4893. Min Range: -0.4893

Max Act: 0.3338. Min Act: -0.0001

Data Index: 1076723 (C4 (Web Text))

Max Activating Token Index: 754

Text #4

Max Range: 0.4893. Min Range: -0.4893

Max Act: 0.3832. Min Act: -0.0001

Data Index: 631060 (C4 (Web Text))

Max Activating Token Index: 288

Text #5

Max Range: 0.4893. Min Range: -0.4893

Max Act: 0.3794. Min Act: -0.0001

Data Index: 1016553 (C4 (Web Text))

Max Activating Token Index: 29

Text #6

Max Range: 0.4893. Min Range: -0.4893

Max Act: 0.3911. Min Act: -0.0001

Data Index: 160601 (C4 (Web Text))

Max Activating Token Index: 806

Text #7

Max Range: 0.4893. Min Range: -0.4893

Max Act: 0.3758. Min Act: -0.0001

Data Index: 611097 (C4 (Web Text))

Max Activating Token Index: 539

Text #8

Max Range: 0.4893. Min Range: -0.4893

Max Act: 0.3844. Min Act: -0.0001

Data Index: 94142 (C4 (Web Text))

Max Activating Token Index: 408

Text #9

Max Range: 0.4893. Min Range: -0.4893

Max Act: 0.3842. Min Act: -0.0001

Data Index: 529339 (C4 (Web Text))

Max Activating Token Index: 559

Text #10

Max Range: 0.4893. Min Range: -0.4893

Max Act: 0.4023. Min Act: -0.0001

Data Index: 334142 (C4 (Web Text))

Max Activating Token Index: 144

Text #11

Max Range: 0.4893. Min Range: -0.4893

Max Act: 0.3931. Min Act: -0.0001

Data Index: 699424 (C4 (Web Text))

Max Activating Token Index: 735

Text #12

Max Range: 0.4893. Min Range: -0.4893

Max Act: 0.3356. Min Act: -0.0001

Data Index: 947545 (C4 (Web Text))

Max Activating Token Index: 799

Text #13

Max Range: 0.4893. Min Range: -0.4893

Max Act: 0.3584. Min Act: -0.0001

Data Index: 871508 (C4 (Web Text))

Max Activating Token Index: 9

Text #14

Max Range: 0.4893. Min Range: -0.4893

Max Act: 0.3985. Min Act: -0.0001

Data Index: 837353 (C4 (Web Text))

Max Activating Token Index: 721

Text #15

Max Range: 0.4893. Min Range: -0.4893

Max Act: 0.3667. Min Act: -0.0001

Data Index: 1122972 (C4 (Web Text))

Max Activating Token Index: 62

Text #16

Max Range: 0.4893. Min Range: -0.4893

Max Act: 0.3774. Min Act: -0.0001

Data Index: 956924 (C4 (Web Text))

Max Activating Token Index: 406

Text #17

Max Range: 0.4893. Min Range: -0.4893

Max Act: 0.3634. Min Act: -0.0001

Data Index: 176106 (C4 (Web Text))

Max Activating Token Index: 30

Text #18

Max Range: 0.4893. Min Range: -0.4893

Max Act: 0.3770. Min Act: -0.0001

Data Index: 1323826 (C4 (Web Text))

Max Activating Token Index: 446

Text #19

Max Range: 0.4893. Min Range: -0.4893

Max Act: 0.3308. Min Act: -0.0001

Data Index: 711274 (C4 (Web Text))

Max Activating Token Index: 680