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

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

Neuron 173 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5226. Min Range: -0.5226

Max Act: 0.5226. Min Act: -0.0000

Data Index: 952881 (C4 (Web Text))

Max Activating Token Index: 154

Text #1

Max Range: 0.5226. Min Range: -0.5226

Max Act: 0.4856. Min Act: -0.0000

Data Index: 147421 (C4 (Web Text))

Max Activating Token Index: 905

Text #2

Max Range: 0.5226. Min Range: -0.5226

Max Act: 0.4503. Min Act: -0.0000

Data Index: 443209 (C4 (Web Text))

Max Activating Token Index: 603

Text #3

Max Range: 0.5226. Min Range: -0.5226

Max Act: 0.4570. Min Act: -0.0000

Data Index: 611059 (C4 (Web Text))

Max Activating Token Index: 863

Text #4

Max Range: 0.5226. Min Range: -0.5226

Max Act: 0.4026. Min Act: -0.0000

Data Index: 539521 (C4 (Web Text))

Max Activating Token Index: 510

Text #5

Max Range: 0.5226. Min Range: -0.5226

Max Act: 0.4015. Min Act: -0.0000

Data Index: 904919 (C4 (Web Text))

Max Activating Token Index: 214

Text #6

Max Range: 0.5226. Min Range: -0.5226

Max Act: 0.4335. Min Act: -0.0000

Data Index: 1351055 (C4 (Web Text))

Max Activating Token Index: 993

Text #7

Max Range: 0.5226. Min Range: -0.5226

Max Act: 0.3875. Min Act: -0.0000

Data Index: 997980 (C4 (Web Text))

Max Activating Token Index: 823

Text #8

Max Range: 0.5226. Min Range: -0.5226

Max Act: 0.4106. Min Act: -0.0000

Data Index: 230231 (C4 (Web Text))

Max Activating Token Index: 100

Text #9

Max Range: 0.5226. Min Range: -0.5226

Max Act: 0.4207. Min Act: -0.0000

Data Index: 995310 (C4 (Web Text))

Max Activating Token Index: 145

Text #10

Max Range: 0.5226. Min Range: -0.5226

Max Act: 0.3892. Min Act: -0.0000

Data Index: 1556664 (Python Code)

Max Activating Token Index: 234

Text #11

Max Range: 0.5226. Min Range: -0.5226

Max Act: 0.3904. Min Act: -0.0000

Data Index: 346968 (C4 (Web Text))

Max Activating Token Index: 64

Text #12

Max Range: 0.5226. Min Range: -0.5226

Max Act: 0.4018. Min Act: -0.0000

Data Index: 1615844 (Python Code)

Max Activating Token Index: 1004

Text #13

Max Range: 0.5226. Min Range: -0.5226

Max Act: 0.3825. Min Act: -0.0000

Data Index: 503631 (C4 (Web Text))

Max Activating Token Index: 143

Text #14

Max Range: 0.5226. Min Range: -0.5226

Max Act: 0.3437. Min Act: -0.0000

Data Index: 1154697 (C4 (Web Text))

Max Activating Token Index: 581

Text #15

Max Range: 0.5226. Min Range: -0.5226

Max Act: 0.3719. Min Act: -0.0000

Data Index: 1061772 (C4 (Web Text))

Max Activating Token Index: 733

Text #16

Max Range: 0.5226. Min Range: -0.5226

Max Act: 0.3604. Min Act: -0.0000

Data Index: 1023303 (C4 (Web Text))

Max Activating Token Index: 663

Text #17

Max Range: 0.5226. Min Range: -0.5226

Max Act: 0.3720. Min Act: -0.0000

Data Index: 714815 (C4 (Web Text))

Max Activating Token Index: 192

Text #18

Max Range: 0.5226. Min Range: -0.5226

Max Act: 0.3708. Min Act: -0.0000

Data Index: 609907 (C4 (Web Text))

Max Activating Token Index: 109

Text #19

Max Range: 0.5226. Min Range: -0.5226

Max Act: 0.3538. Min Act: -0.0000

Data Index: 110992 (C4 (Web Text))

Max Activating Token Index: 854