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

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

Neuron 1604 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.9623. Min Act: -0.0001

Data Index: 549507 (C4 (Web Text))

Max Activating Token Index: 530

Text #1

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.8636. Min Act: -0.0001

Data Index: 46130 (C4 (Web Text))

Max Activating Token Index: 172

Text #2

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.9190. Min Act: -0.0001

Data Index: 263443 (C4 (Web Text))

Max Activating Token Index: 750

Text #3

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.8057. Min Act: -0.0001

Data Index: 370164 (C4 (Web Text))

Max Activating Token Index: 537

Text #4

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.7065. Min Act: -0.0001

Data Index: 323988 (C4 (Web Text))

Max Activating Token Index: 887

Text #5

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.7719. Min Act: -0.0001

Data Index: 239102 (C4 (Web Text))

Max Activating Token Index: 641

Text #6

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.7101. Min Act: -0.0001

Data Index: 1115659 (C4 (Web Text))

Max Activating Token Index: 120

Text #7

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.7083. Min Act: -0.0001

Data Index: 820233 (C4 (Web Text))

Max Activating Token Index: 728

Text #8

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.7061. Min Act: -0.0001

Data Index: 473131 (C4 (Web Text))

Max Activating Token Index: 546

Text #9

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.6765. Min Act: -0.0001

Data Index: 176955 (C4 (Web Text))

Max Activating Token Index: 83

Text #10

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.6014. Min Act: -0.0001

Data Index: 374548 (C4 (Web Text))

Max Activating Token Index: 888

Text #11

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.6263. Min Act: -0.0001

Data Index: 822481 (C4 (Web Text))

Max Activating Token Index: 906

Text #12

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.5808. Min Act: -0.0001

Data Index: 293877 (C4 (Web Text))

Max Activating Token Index: 745

Text #13

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.5730. Min Act: -0.0001

Data Index: 404277 (C4 (Web Text))

Max Activating Token Index: 554

Text #14

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.6241. Min Act: -0.0001

Data Index: 578603 (C4 (Web Text))

Max Activating Token Index: 214

Text #15

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.6201. Min Act: -0.0001

Data Index: 996219 (C4 (Web Text))

Max Activating Token Index: 348

Text #16

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.5421. Min Act: -0.0001

Data Index: 340676 (C4 (Web Text))

Max Activating Token Index: 1013

Text #17

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.5139. Min Act: -0.0001

Data Index: 204907 (C4 (Web Text))

Max Activating Token Index: 915

Text #18

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.5587. Min Act: -0.0001

Data Index: 1009133 (C4 (Web Text))

Max Activating Token Index: 149

Text #19

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.5559. Min Act: -0.0001

Data Index: 1003002 (C4 (Web Text))

Max Activating Token Index: 17