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

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

Neuron 1554 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: 0.7518. Min Range: -0.7518

Max Act: 0.6767. Min Act: -0.0001

Data Index: 450237 (C4 (Web Text))

Max Activating Token Index: 37

Text #1

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.6697. Min Act: -0.0001

Data Index: 852854 (C4 (Web Text))

Max Activating Token Index: 74

Text #2

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.6838. Min Act: -0.0001

Data Index: 1114627 (C4 (Web Text))

Max Activating Token Index: 1006

Text #3

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.6809. Min Act: -0.0001

Data Index: 332252 (C4 (Web Text))

Max Activating Token Index: 643

Text #4

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.7518. Min Act: -0.0001

Data Index: 711721 (C4 (Web Text))

Max Activating Token Index: 951

Text #5

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.6811. Min Act: -0.0001

Data Index: 1150315 (C4 (Web Text))

Max Activating Token Index: 43

Text #6

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.5772. Min Act: -0.0001

Data Index: 26645 (C4 (Web Text))

Max Activating Token Index: 725

Text #7

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.6401. Min Act: -0.0001

Data Index: 175288 (C4 (Web Text))

Max Activating Token Index: 463

Text #8

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.6258. Min Act: -0.0001

Data Index: 613655 (C4 (Web Text))

Max Activating Token Index: 933

Text #9

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.6885. Min Act: -0.0001

Data Index: 897265 (C4 (Web Text))

Max Activating Token Index: 839

Text #10

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.6425. Min Act: -0.0001

Data Index: 1070233 (C4 (Web Text))

Max Activating Token Index: 82

Text #11

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.6722. Min Act: -0.0001

Data Index: 1293454 (C4 (Web Text))

Max Activating Token Index: 204

Text #12

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.5865. Min Act: -0.0001

Data Index: 893866 (C4 (Web Text))

Max Activating Token Index: 568

Text #13

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.6328. Min Act: -0.0001

Data Index: 471606 (C4 (Web Text))

Max Activating Token Index: 356

Text #14

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.6799. Min Act: -0.0001

Data Index: 1271233 (C4 (Web Text))

Max Activating Token Index: 229

Text #15

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.5628. Min Act: -0.0001

Data Index: 953454 (C4 (Web Text))

Max Activating Token Index: 612

Text #16

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.6053. Min Act: -0.0001

Data Index: 136349 (C4 (Web Text))

Max Activating Token Index: 780

Text #17

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.6060. Min Act: -0.0001

Data Index: 559623 (C4 (Web Text))

Max Activating Token Index: 842

Text #18

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.5608. Min Act: -0.0001

Data Index: 187418 (C4 (Web Text))

Max Activating Token Index: 956

Text #19

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.5990. Min Act: -0.0001

Data Index: 904173 (C4 (Web Text))

Max Activating Token Index: 469