Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 776 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3895. Min Act: -0.0004

Data Index: 450229 (C4 (Web Text))

Max Activating Token Index: 788

Text #1

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3875. Min Act: -0.0004

Data Index: 157012 (C4 (Web Text))

Max Activating Token Index: 842

Text #2

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3801. Min Act: -0.0004

Data Index: 943280 (C4 (Web Text))

Max Activating Token Index: 444

Text #3

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3747. Min Act: -0.0004

Data Index: 607554 (C4 (Web Text))

Max Activating Token Index: 388

Text #4

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3791. Min Act: -0.0004

Data Index: 731922 (C4 (Web Text))

Max Activating Token Index: 50

Text #5

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3628. Min Act: -0.0004

Data Index: 825109 (C4 (Web Text))

Max Activating Token Index: 671

Text #6

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3749. Min Act: -0.0004

Data Index: 1085194 (C4 (Web Text))

Max Activating Token Index: 373

Text #7

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3614. Min Act: -0.0004

Data Index: 1138001 (C4 (Web Text))

Max Activating Token Index: 683

Text #8

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3598. Min Act: -0.0004

Data Index: 574862 (C4 (Web Text))

Max Activating Token Index: 61

Text #9

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3592. Min Act: -0.0004

Data Index: 925019 (C4 (Web Text))

Max Activating Token Index: 200

Text #10

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3487. Min Act: -0.0004

Data Index: 335646 (C4 (Web Text))

Max Activating Token Index: 543

Text #11

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3349. Min Act: -0.0004

Data Index: 683846 (C4 (Web Text))

Max Activating Token Index: 905

Text #12

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3451. Min Act: -0.0004

Data Index: 66528 (C4 (Web Text))

Max Activating Token Index: 984

Text #13

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3332. Min Act: -0.0004

Data Index: 477024 (C4 (Web Text))

Max Activating Token Index: 815

Text #14

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3445. Min Act: -0.0004

Data Index: 937927 (C4 (Web Text))

Max Activating Token Index: 332

Text #15

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3439. Min Act: -0.0004

Data Index: 1315361 (C4 (Web Text))

Max Activating Token Index: 72

Text #16

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3434. Min Act: -0.0004

Data Index: 308854 (C4 (Web Text))

Max Activating Token Index: 548

Text #17

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3551. Min Act: -0.0004

Data Index: 1332761 (C4 (Web Text))

Max Activating Token Index: 777

Text #18

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3429. Min Act: -0.0004

Data Index: 102103 (C4 (Web Text))

Max Activating Token Index: 109

Text #19

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3421. Min Act: -0.0004

Data Index: 1106543 (C4 (Web Text))

Max Activating Token Index: 957