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

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

Neuron 4235 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0042. Min Range: -1.0042

Max Act: 1.0042. Min Act: -0.0001

Data Index: 1576120 (Python Code)

Max Activating Token Index: 533

Text #1

Max Range: 1.0042. Min Range: -1.0042

Max Act: 0.9770. Min Act: -0.0001

Data Index: 1608265 (Python Code)

Max Activating Token Index: 766

Text #2

Max Range: 1.0042. Min Range: -1.0042

Max Act: 0.9267. Min Act: -0.0001

Data Index: 1623771 (Python Code)

Max Activating Token Index: 255

Text #3

Max Range: 1.0042. Min Range: -1.0042

Max Act: 0.8684. Min Act: -0.0001

Data Index: 1597331 (Python Code)

Max Activating Token Index: 156

Text #4

Max Range: 1.0042. Min Range: -1.0042

Max Act: 0.8871. Min Act: -0.0001

Data Index: 1656601 (Python Code)

Max Activating Token Index: 383

Text #5

Max Range: 1.0042. Min Range: -1.0042

Max Act: 0.7889. Min Act: -0.0001

Data Index: 723112 (C4 (Web Text))

Max Activating Token Index: 526

Text #6

Max Range: 1.0042. Min Range: -1.0042

Max Act: 0.8386. Min Act: -0.0001

Data Index: 1624805 (Python Code)

Max Activating Token Index: 193

Text #7

Max Range: 1.0042. Min Range: -1.0042

Max Act: 0.7731. Min Act: -0.0001

Data Index: 568956 (C4 (Web Text))

Max Activating Token Index: 29

Text #8

Max Range: 1.0042. Min Range: -1.0042

Max Act: 0.8095. Min Act: -0.0001

Data Index: 1458426 (Python Code)

Max Activating Token Index: 23

Text #9

Max Range: 1.0042. Min Range: -1.0042

Max Act: 0.7276. Min Act: -0.0001

Data Index: 250282 (C4 (Web Text))

Max Activating Token Index: 895

Text #10

Max Range: 1.0042. Min Range: -1.0042

Max Act: 0.7470. Min Act: -0.0001

Data Index: 475249 (C4 (Web Text))

Max Activating Token Index: 930

Text #11

Max Range: 1.0042. Min Range: -1.0042

Max Act: 0.7235. Min Act: -0.0001

Data Index: 249146 (C4 (Web Text))

Max Activating Token Index: 986

Text #12

Max Range: 1.0042. Min Range: -1.0042

Max Act: 0.7561. Min Act: -0.0001

Data Index: 414517 (C4 (Web Text))

Max Activating Token Index: 22

Text #13

Max Range: 1.0042. Min Range: -1.0042

Max Act: 0.7875. Min Act: -0.0001

Data Index: 1480311 (Python Code)

Max Activating Token Index: 336

Text #14

Max Range: 1.0042. Min Range: -1.0042

Max Act: 0.6988. Min Act: -0.0001

Data Index: 927878 (C4 (Web Text))

Max Activating Token Index: 577

Text #15

Max Range: 1.0042. Min Range: -1.0042

Max Act: 0.7099. Min Act: -0.0001

Data Index: 266494 (C4 (Web Text))

Max Activating Token Index: 906

Text #16

Max Range: 1.0042. Min Range: -1.0042

Max Act: 0.6719. Min Act: -0.0001

Data Index: 211013 (C4 (Web Text))

Max Activating Token Index: 649

Text #17

Max Range: 1.0042. Min Range: -1.0042

Max Act: 0.6824. Min Act: -0.0001

Data Index: 917040 (C4 (Web Text))

Max Activating Token Index: 970

Text #18

Max Range: 1.0042. Min Range: -1.0042

Max Act: 0.6837. Min Act: -0.0001

Data Index: 725983 (C4 (Web Text))

Max Activating Token Index: 658

Text #19

Max Range: 1.0042. Min Range: -1.0042

Max Act: 0.7206. Min Act: -0.0001

Data Index: 299184 (C4 (Web Text))

Max Activating Token Index: 479