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

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

Neuron 2030 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: 1.9664. Min Range: -1.9664

Max Act: 1.9664. Min Act: -0.0001

Data Index: 344009 (C4 (Web Text))

Max Activating Token Index: 613

Text #1

Max Range: 1.9664. Min Range: -1.9664

Max Act: 1.8614. Min Act: -0.0001

Data Index: 1082449 (C4 (Web Text))

Max Activating Token Index: 847

Text #2

Max Range: 1.9664. Min Range: -1.9664

Max Act: 1.9343. Min Act: -0.0001

Data Index: 1063740 (C4 (Web Text))

Max Activating Token Index: 822

Text #3

Max Range: 1.9664. Min Range: -1.9664

Max Act: 1.6614. Min Act: -0.0001

Data Index: 1122188 (C4 (Web Text))

Max Activating Token Index: 229

Text #4

Max Range: 1.9664. Min Range: -1.9664

Max Act: 1.6214. Min Act: -0.0001

Data Index: 218009 (C4 (Web Text))

Max Activating Token Index: 850

Text #5

Max Range: 1.9664. Min Range: -1.9664

Max Act: 1.6634. Min Act: -0.0001

Data Index: 795196 (C4 (Web Text))

Max Activating Token Index: 538

Text #6

Max Range: 1.9664. Min Range: -1.9664

Max Act: 1.5615. Min Act: -0.0001

Data Index: 347654 (C4 (Web Text))

Max Activating Token Index: 27

Text #7

Max Range: 1.9664. Min Range: -1.9664

Max Act: 1.5816. Min Act: -0.0001

Data Index: 1220109 (C4 (Web Text))

Max Activating Token Index: 586

Text #8

Max Range: 1.9664. Min Range: -1.9664

Max Act: 1.6799. Min Act: -0.0001

Data Index: 75567 (C4 (Web Text))

Max Activating Token Index: 992

Text #9

Max Range: 1.9664. Min Range: -1.9664

Max Act: 1.5393. Min Act: -0.0001

Data Index: 448841 (C4 (Web Text))

Max Activating Token Index: 801

Text #10

Max Range: 1.9664. Min Range: -1.9664

Max Act: 1.6159. Min Act: -0.0001

Data Index: 1091626 (C4 (Web Text))

Max Activating Token Index: 253

Text #11

Max Range: 1.9664. Min Range: -1.9664

Max Act: 1.5141. Min Act: -0.0001

Data Index: 1076850 (C4 (Web Text))

Max Activating Token Index: 390

Text #12

Max Range: 1.9664. Min Range: -1.9664

Max Act: 1.4594. Min Act: -0.0001

Data Index: 135105 (C4 (Web Text))

Max Activating Token Index: 680

Text #13

Max Range: 1.9664. Min Range: -1.9664

Max Act: 1.5477. Min Act: -0.0001

Data Index: 53338 (C4 (Web Text))

Max Activating Token Index: 218

Text #14

Max Range: 1.9664. Min Range: -1.9664

Max Act: 1.5380. Min Act: -0.0001

Data Index: 623073 (C4 (Web Text))

Max Activating Token Index: 343

Text #15

Max Range: 1.9664. Min Range: -1.9664

Max Act: 1.5787. Min Act: -0.0001

Data Index: 657478 (C4 (Web Text))

Max Activating Token Index: 322

Text #16

Max Range: 1.9664. Min Range: -1.9664

Max Act: 1.5403. Min Act: -0.0001

Data Index: 598389 (C4 (Web Text))

Max Activating Token Index: 974

Text #17

Max Range: 1.9664. Min Range: -1.9664

Max Act: 1.4794. Min Act: -0.0001

Data Index: 1263391 (C4 (Web Text))

Max Activating Token Index: 920

Text #18

Max Range: 1.9664. Min Range: -1.9664

Max Act: 1.4128. Min Act: -0.0001

Data Index: 1150042 (C4 (Web Text))

Max Activating Token Index: 732

Text #19

Max Range: 1.9664. Min Range: -1.9664

Max Act: 1.5066. Min Act: -0.0001

Data Index: 648817 (C4 (Web Text))

Max Activating Token Index: 584