Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3404 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.1111. Min Range: -1.1111

Max Act: 0.9804. Min Act: -0.0001

Data Index: 207807 (C4 (Web Text))

Max Activating Token Index: 801

Text #1

Max Range: 1.1111. Min Range: -1.1111

Max Act: 0.9394. Min Act: -0.0001

Data Index: 916597 (C4 (Web Text))

Max Activating Token Index: 695

Text #2

Max Range: 1.1111. Min Range: -1.1111

Max Act: 1.1111. Min Act: -0.0001

Data Index: 907913 (C4 (Web Text))

Max Activating Token Index: 867

Text #3

Max Range: 1.1111. Min Range: -1.1111

Max Act: 0.9335. Min Act: -0.0001

Data Index: 1355811 (C4 (Web Text))

Max Activating Token Index: 1005

Text #4

Max Range: 1.1111. Min Range: -1.1111

Max Act: 0.8928. Min Act: -0.0001

Data Index: 789850 (C4 (Web Text))

Max Activating Token Index: 193

Text #5

Max Range: 1.1111. Min Range: -1.1111

Max Act: 0.9921. Min Act: -0.0001

Data Index: 754283 (C4 (Web Text))

Max Activating Token Index: 725

Text #6

Max Range: 1.1111. Min Range: -1.1111

Max Act: 0.9210. Min Act: -0.0001

Data Index: 1081334 (C4 (Web Text))

Max Activating Token Index: 940

Text #7

Max Range: 1.1111. Min Range: -1.1111

Max Act: 0.6293. Min Act: -0.0001

Data Index: 419591 (C4 (Web Text))

Max Activating Token Index: 373

Text #8

Max Range: 1.1111. Min Range: -1.1111

Max Act: 1.0008. Min Act: -0.0001

Data Index: 803852 (C4 (Web Text))

Max Activating Token Index: 923

Text #9

Max Range: 1.1111. Min Range: -1.1111

Max Act: 0.7353. Min Act: -0.0001

Data Index: 1294039 (C4 (Web Text))

Max Activating Token Index: 902

Text #10

Max Range: 1.1111. Min Range: -1.1111

Max Act: 0.9918. Min Act: -0.0001

Data Index: 604027 (C4 (Web Text))

Max Activating Token Index: 355

Text #11

Max Range: 1.1111. Min Range: -1.1111

Max Act: 0.9156. Min Act: -0.0001

Data Index: 382619 (C4 (Web Text))

Max Activating Token Index: 985

Text #12

Max Range: 1.1111. Min Range: -1.1111

Max Act: 1.0502. Min Act: -0.0001

Data Index: 237487 (C4 (Web Text))

Max Activating Token Index: 332

Text #13

Max Range: 1.1111. Min Range: -1.1111

Max Act: 0.9332. Min Act: -0.0001

Data Index: 969145 (C4 (Web Text))

Max Activating Token Index: 474

Text #14

Max Range: 1.1111. Min Range: -1.1111

Max Act: 0.9361. Min Act: -0.0001

Data Index: 190850 (C4 (Web Text))

Max Activating Token Index: 599

Text #15

Max Range: 1.1111. Min Range: -1.1111

Max Act: 0.8406. Min Act: -0.0001

Data Index: 15861 (C4 (Web Text))

Max Activating Token Index: 821

Text #16

Max Range: 1.1111. Min Range: -1.1111

Max Act: 0.9166. Min Act: -0.0001

Data Index: 1281450 (C4 (Web Text))

Max Activating Token Index: 192

Text #17

Max Range: 1.1111. Min Range: -1.1111

Max Act: 0.8974. Min Act: -0.0001

Data Index: 946778 (C4 (Web Text))

Max Activating Token Index: 971

Text #18

Max Range: 1.1111. Min Range: -1.1111

Max Act: 0.9084. Min Act: -0.0001

Data Index: 160996 (C4 (Web Text))

Max Activating Token Index: 904

Text #19

Max Range: 1.1111. Min Range: -1.1111

Max Act: 0.9277. Min Act: -0.0001

Data Index: 705900 (C4 (Web Text))

Max Activating Token Index: 668