Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 845 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0693. Min Act: -0.0003

Data Index: 349349 (C4 (Web Text))

Max Activating Token Index: 980

Text #1

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0606. Min Act: -0.0003

Data Index: 1319796 (C4 (Web Text))

Max Activating Token Index: 148

Text #2

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0603. Min Act: -0.0003

Data Index: 1190058 (C4 (Web Text))

Max Activating Token Index: 892

Text #3

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0569. Min Act: -0.0003

Data Index: 841585 (C4 (Web Text))

Max Activating Token Index: 437

Text #4

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0558. Min Act: -0.0003

Data Index: 273670 (C4 (Web Text))

Max Activating Token Index: 684

Text #5

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0531. Min Act: -0.0003

Data Index: 961710 (C4 (Web Text))

Max Activating Token Index: 571

Text #6

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0527. Min Act: -0.0002

Data Index: 1046333 (C4 (Web Text))

Max Activating Token Index: 972

Text #7

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0519. Min Act: -0.0002

Data Index: 866137 (C4 (Web Text))

Max Activating Token Index: 60

Text #8

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0524. Min Act: -0.0003

Data Index: 56757 (C4 (Web Text))

Max Activating Token Index: 685

Text #9

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0518. Min Act: -0.0003

Data Index: 1021080 (C4 (Web Text))

Max Activating Token Index: 604

Text #10

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0537. Min Act: -0.0004

Data Index: 216486 (C4 (Web Text))

Max Activating Token Index: 869

Text #11

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0510. Min Act: -0.0003

Data Index: 1358512 (C4 (Web Text))

Max Activating Token Index: 1011

Text #12

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0524. Min Act: -0.0002

Data Index: 1135770 (C4 (Web Text))

Max Activating Token Index: 29

Text #13

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0524. Min Act: -0.0002

Data Index: 301832 (C4 (Web Text))

Max Activating Token Index: 420

Text #14

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0507. Min Act: -0.0003

Data Index: 608926 (C4 (Web Text))

Max Activating Token Index: 27

Text #15

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0512. Min Act: -0.0004

Data Index: 1061089 (C4 (Web Text))

Max Activating Token Index: 845

Text #16

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0506. Min Act: -0.0003

Data Index: 832424 (C4 (Web Text))

Max Activating Token Index: 93

Text #17

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0494. Min Act: -0.0003

Data Index: 1354974 (C4 (Web Text))

Max Activating Token Index: 447

Text #18

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0523. Min Act: -0.0003

Data Index: 1124762 (C4 (Web Text))

Max Activating Token Index: 225

Text #19

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0498. Min Act: -0.0003

Data Index: 108837 (C4 (Web Text))

Max Activating Token Index: 770