Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 744 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5586. Min Range: -0.5586

Max Act: 0.5586. Min Act: -0.0001

Data Index: 387815 (C4 (Web Text))

Max Activating Token Index: 819

Text #1

Max Range: 0.5586. Min Range: -0.5586

Max Act: 0.4884. Min Act: -0.0001

Data Index: 128820 (C4 (Web Text))

Max Activating Token Index: 368

Text #2

Max Range: 0.5586. Min Range: -0.5586

Max Act: 0.5274. Min Act: -0.0001

Data Index: 1000665 (C4 (Web Text))

Max Activating Token Index: 1022

Text #3

Max Range: 0.5586. Min Range: -0.5586

Max Act: 0.4950. Min Act: -0.0001

Data Index: 444939 (C4 (Web Text))

Max Activating Token Index: 156

Text #4

Max Range: 0.5586. Min Range: -0.5586

Max Act: 0.4880. Min Act: -0.0001

Data Index: 862376 (C4 (Web Text))

Max Activating Token Index: 787

Text #5

Max Range: 0.5586. Min Range: -0.5586

Max Act: 0.4846. Min Act: -0.0001

Data Index: 496311 (C4 (Web Text))

Max Activating Token Index: 807

Text #6

Max Range: 0.5586. Min Range: -0.5586

Max Act: 0.4801. Min Act: -0.0001

Data Index: 710737 (C4 (Web Text))

Max Activating Token Index: 835

Text #7

Max Range: 0.5586. Min Range: -0.5586

Max Act: 0.4746. Min Act: -0.0001

Data Index: 235914 (C4 (Web Text))

Max Activating Token Index: 896

Text #8

Max Range: 0.5586. Min Range: -0.5586

Max Act: 0.4770. Min Act: -0.0001

Data Index: 105148 (C4 (Web Text))

Max Activating Token Index: 838

Text #9

Max Range: 0.5586. Min Range: -0.5586

Max Act: 0.4783. Min Act: -0.0001

Data Index: 99762 (C4 (Web Text))

Max Activating Token Index: 799

Text #10

Max Range: 0.5586. Min Range: -0.5586

Max Act: 0.5030. Min Act: -0.0001

Data Index: 1038844 (C4 (Web Text))

Max Activating Token Index: 196

Text #11

Max Range: 0.5586. Min Range: -0.5586

Max Act: 0.4672. Min Act: -0.0001

Data Index: 901328 (C4 (Web Text))

Max Activating Token Index: 925

Text #12

Max Range: 0.5586. Min Range: -0.5586

Max Act: 0.4782. Min Act: -0.0001

Data Index: 790102 (C4 (Web Text))

Max Activating Token Index: 386

Text #13

Max Range: 0.5586. Min Range: -0.5586

Max Act: 0.4633. Min Act: -0.0001

Data Index: 529221 (C4 (Web Text))

Max Activating Token Index: 231

Text #14

Max Range: 0.5586. Min Range: -0.5586

Max Act: 0.4614. Min Act: -0.0001

Data Index: 1160140 (C4 (Web Text))

Max Activating Token Index: 582

Text #15

Max Range: 0.5586. Min Range: -0.5586

Max Act: 0.4620. Min Act: -0.0001

Data Index: 184115 (C4 (Web Text))

Max Activating Token Index: 785

Text #16

Max Range: 0.5586. Min Range: -0.5586

Max Act: 0.4546. Min Act: -0.0001

Data Index: 757256 (C4 (Web Text))

Max Activating Token Index: 870

Text #17

Max Range: 0.5586. Min Range: -0.5586

Max Act: 0.4743. Min Act: -0.0001

Data Index: 1344850 (C4 (Web Text))

Max Activating Token Index: 360

Text #18

Max Range: 0.5586. Min Range: -0.5586

Max Act: 0.4558. Min Act: -0.0001

Data Index: 367212 (C4 (Web Text))

Max Activating Token Index: 625

Text #19

Max Range: 0.5586. Min Range: -0.5586

Max Act: 0.4552. Min Act: -0.0001

Data Index: 305369 (C4 (Web Text))

Max Activating Token Index: 118