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

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

Neuron 387 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4859. Min Range: -0.4859

Max Act: 0.4859. Min Act: -0.0002

Data Index: 759866 (C4 (Web Text))

Max Activating Token Index: 624

Text #1

Max Range: 0.4859. Min Range: -0.4859

Max Act: 0.4622. Min Act: -0.0002

Data Index: 735646 (C4 (Web Text))

Max Activating Token Index: 322

Text #2

Max Range: 0.4859. Min Range: -0.4859

Max Act: 0.4048. Min Act: -0.0002

Data Index: 722150 (C4 (Web Text))

Max Activating Token Index: 735

Text #3

Max Range: 0.4859. Min Range: -0.4859

Max Act: 0.4383. Min Act: -0.0002

Data Index: 12149 (C4 (Web Text))

Max Activating Token Index: 24

Text #4

Max Range: 0.4859. Min Range: -0.4859

Max Act: 0.4239. Min Act: -0.0002

Data Index: 603298 (C4 (Web Text))

Max Activating Token Index: 144

Text #5

Max Range: 0.4859. Min Range: -0.4859

Max Act: 0.4401. Min Act: -0.0002

Data Index: 909682 (C4 (Web Text))

Max Activating Token Index: 846

Text #6

Max Range: 0.4859. Min Range: -0.4859

Max Act: 0.4193. Min Act: -0.0002

Data Index: 1292945 (C4 (Web Text))

Max Activating Token Index: 312

Text #7

Max Range: 0.4859. Min Range: -0.4859

Max Act: 0.4324. Min Act: -0.0002

Data Index: 1083547 (C4 (Web Text))

Max Activating Token Index: 501

Text #8

Max Range: 0.4859. Min Range: -0.4859

Max Act: 0.3909. Min Act: -0.0002

Data Index: 511171 (C4 (Web Text))

Max Activating Token Index: 511

Text #9

Max Range: 0.4859. Min Range: -0.4859

Max Act: 0.3966. Min Act: -0.0002

Data Index: 858509 (C4 (Web Text))

Max Activating Token Index: 924

Text #10

Max Range: 0.4859. Min Range: -0.4859

Max Act: 0.3740. Min Act: -0.0002

Data Index: 1073568 (C4 (Web Text))

Max Activating Token Index: 276

Text #11

Max Range: 0.4859. Min Range: -0.4859

Max Act: 0.3892. Min Act: -0.0002

Data Index: 613940 (C4 (Web Text))

Max Activating Token Index: 449

Text #12

Max Range: 0.4859. Min Range: -0.4859

Max Act: 0.4146. Min Act: -0.0002

Data Index: 232364 (C4 (Web Text))

Max Activating Token Index: 594

Text #13

Max Range: 0.4859. Min Range: -0.4859

Max Act: 0.3710. Min Act: -0.0002

Data Index: 650039 (C4 (Web Text))

Max Activating Token Index: 750

Text #14

Max Range: 0.4859. Min Range: -0.4859

Max Act: 0.3909. Min Act: -0.0002

Data Index: 335863 (C4 (Web Text))

Max Activating Token Index: 32

Text #15

Max Range: 0.4859. Min Range: -0.4859

Max Act: 0.4017. Min Act: -0.0002

Data Index: 90710 (C4 (Web Text))

Max Activating Token Index: 61

Text #16

Max Range: 0.4859. Min Range: -0.4859

Max Act: 0.4020. Min Act: -0.0002

Data Index: 433859 (C4 (Web Text))

Max Activating Token Index: 707

Text #17

Max Range: 0.4859. Min Range: -0.4859

Max Act: 0.3378. Min Act: -0.0002

Data Index: 761979 (C4 (Web Text))

Max Activating Token Index: 401

Text #18

Max Range: 0.4859. Min Range: -0.4859

Max Act: 0.3707. Min Act: -0.0002

Data Index: 12640 (C4 (Web Text))

Max Activating Token Index: 552

Text #19

Max Range: 0.4859. Min Range: -0.4859

Max Act: 0.3902. Min Act: -0.0002

Data Index: 253684 (C4 (Web Text))

Max Activating Token Index: 767