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

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

Neuron 3832 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3744. Min Range: -0.3744

Max Act: 0.3744. Min Act: -0.0001

Data Index: 569732 (C4 (Web Text))

Max Activating Token Index: 947

Text #1

Max Range: 0.3744. Min Range: -0.3744

Max Act: 0.3486. Min Act: -0.0000

Data Index: 782131 (C4 (Web Text))

Max Activating Token Index: 985

Text #2

Max Range: 0.3744. Min Range: -0.3744

Max Act: 0.3415. Min Act: -0.0001

Data Index: 230847 (C4 (Web Text))

Max Activating Token Index: 530

Text #3

Max Range: 0.3744. Min Range: -0.3744

Max Act: 0.3263. Min Act: -0.0000

Data Index: 476345 (C4 (Web Text))

Max Activating Token Index: 888

Text #4

Max Range: 0.3744. Min Range: -0.3744

Max Act: 0.3204. Min Act: -0.0000

Data Index: 695635 (C4 (Web Text))

Max Activating Token Index: 648

Text #5

Max Range: 0.3744. Min Range: -0.3744

Max Act: 0.3100. Min Act: -0.0000

Data Index: 867305 (C4 (Web Text))

Max Activating Token Index: 349

Text #6

Max Range: 0.3744. Min Range: -0.3744

Max Act: 0.3079. Min Act: -0.0000

Data Index: 1343800 (C4 (Web Text))

Max Activating Token Index: 660

Text #7

Max Range: 0.3744. Min Range: -0.3744

Max Act: 0.3050. Min Act: -0.0001

Data Index: 542339 (C4 (Web Text))

Max Activating Token Index: 696

Text #8

Max Range: 0.3744. Min Range: -0.3744

Max Act: 0.3011. Min Act: -0.0000

Data Index: 456120 (C4 (Web Text))

Max Activating Token Index: 302

Text #9

Max Range: 0.3744. Min Range: -0.3744

Max Act: 0.2863. Min Act: -0.0000

Data Index: 837001 (C4 (Web Text))

Max Activating Token Index: 649

Text #10

Max Range: 0.3744. Min Range: -0.3744

Max Act: 0.2921. Min Act: 0.0000

Data Index: 187607 (C4 (Web Text))

Max Activating Token Index: 910

Text #11

Max Range: 0.3744. Min Range: -0.3744

Max Act: 0.2913. Min Act: -0.0000

Data Index: 859025 (C4 (Web Text))

Max Activating Token Index: 502

Text #12

Max Range: 0.3744. Min Range: -0.3744

Max Act: 0.2974. Min Act: -0.0000

Data Index: 1011945 (C4 (Web Text))

Max Activating Token Index: 993

Text #13

Max Range: 0.3744. Min Range: -0.3744

Max Act: 0.2678. Min Act: -0.0000

Data Index: 670887 (C4 (Web Text))

Max Activating Token Index: 335

Text #14

Max Range: 0.3744. Min Range: -0.3744

Max Act: 0.2877. Min Act: -0.0000

Data Index: 946438 (C4 (Web Text))

Max Activating Token Index: 732

Text #15

Max Range: 0.3744. Min Range: -0.3744

Max Act: 0.2857. Min Act: -0.0000

Data Index: 82107 (C4 (Web Text))

Max Activating Token Index: 317

Text #16

Max Range: 0.3744. Min Range: -0.3744

Max Act: 0.2906. Min Act: -0.0001

Data Index: 604851 (C4 (Web Text))

Max Activating Token Index: 936

Text #17

Max Range: 0.3744. Min Range: -0.3744

Max Act: 0.2821. Min Act: -0.0000

Data Index: 324881 (C4 (Web Text))

Max Activating Token Index: 261

Text #18

Max Range: 0.3744. Min Range: -0.3744

Max Act: 0.2806. Min Act: -0.0001

Data Index: 211116 (C4 (Web Text))

Max Activating Token Index: 330

Text #19

Max Range: 0.3744. Min Range: -0.3744

Max Act: 0.2796. Min Act: -0.0001

Data Index: 91566 (C4 (Web Text))

Max Activating Token Index: 399