Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2002 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6430. Min Range: -0.6430

Max Act: 0.6430. Min Act: -0.0001

Data Index: 406299 (C4 (Web Text))

Max Activating Token Index: 461

Text #1

Max Range: 0.6430. Min Range: -0.6430

Max Act: 0.5927. Min Act: -0.0001

Data Index: 1344665 (C4 (Web Text))

Max Activating Token Index: 672

Text #2

Max Range: 0.6430. Min Range: -0.6430

Max Act: 0.4969. Min Act: -0.0001

Data Index: 138486 (C4 (Web Text))

Max Activating Token Index: 598

Text #3

Max Range: 0.6430. Min Range: -0.6430

Max Act: 0.5317. Min Act: -0.0001

Data Index: 248822 (C4 (Web Text))

Max Activating Token Index: 653

Text #4

Max Range: 0.6430. Min Range: -0.6430

Max Act: 0.5148. Min Act: -0.0001

Data Index: 144696 (C4 (Web Text))

Max Activating Token Index: 139

Text #5

Max Range: 0.6430. Min Range: -0.6430

Max Act: 0.4882. Min Act: -0.0001

Data Index: 1351509 (C4 (Web Text))

Max Activating Token Index: 1004

Text #6

Max Range: 0.6430. Min Range: -0.6430

Max Act: 0.5193. Min Act: -0.0001

Data Index: 1104218 (C4 (Web Text))

Max Activating Token Index: 679

Text #7

Max Range: 0.6430. Min Range: -0.6430

Max Act: 0.4932. Min Act: -0.0001

Data Index: 990256 (C4 (Web Text))

Max Activating Token Index: 16

Text #8

Max Range: 0.6430. Min Range: -0.6430

Max Act: 0.4875. Min Act: -0.0001

Data Index: 1025268 (C4 (Web Text))

Max Activating Token Index: 916

Text #9

Max Range: 0.6430. Min Range: -0.6430

Max Act: 0.4840. Min Act: -0.0001

Data Index: 783337 (C4 (Web Text))

Max Activating Token Index: 86

Text #10

Max Range: 0.6430. Min Range: -0.6430

Max Act: 0.4799. Min Act: -0.0001

Data Index: 1332397 (C4 (Web Text))

Max Activating Token Index: 200

Text #11

Max Range: 0.6430. Min Range: -0.6430

Max Act: 0.4771. Min Act: -0.0001

Data Index: 1337353 (C4 (Web Text))

Max Activating Token Index: 529

Text #12

Max Range: 0.6430. Min Range: -0.6430

Max Act: 0.5108. Min Act: -0.0001

Data Index: 360756 (C4 (Web Text))

Max Activating Token Index: 651

Text #13

Max Range: 0.6430. Min Range: -0.6430

Max Act: 0.4853. Min Act: -0.0001

Data Index: 204013 (C4 (Web Text))

Max Activating Token Index: 488

Text #14

Max Range: 0.6430. Min Range: -0.6430

Max Act: 0.4576. Min Act: -0.0001

Data Index: 410048 (C4 (Web Text))

Max Activating Token Index: 359

Text #15

Max Range: 0.6430. Min Range: -0.6430

Max Act: 0.4689. Min Act: -0.0001

Data Index: 231518 (C4 (Web Text))

Max Activating Token Index: 913

Text #16

Max Range: 0.6430. Min Range: -0.6430

Max Act: 0.4995. Min Act: -0.0001

Data Index: 454304 (C4 (Web Text))

Max Activating Token Index: 238

Text #17

Max Range: 0.6430. Min Range: -0.6430

Max Act: 0.4791. Min Act: 0.0001

Data Index: 80660 (C4 (Web Text))

Max Activating Token Index: 586

Text #18

Max Range: 0.6430. Min Range: -0.6430

Max Act: 0.4610. Min Act: -0.0001

Data Index: 883133 (C4 (Web Text))

Max Activating Token Index: 812

Text #19

Max Range: 0.6430. Min Range: -0.6430

Max Act: 0.4550. Min Act: -0.0001

Data Index: 151137 (C4 (Web Text))

Max Activating Token Index: 970