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

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

Neuron 5662 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6778. Min Range: -0.6778

Max Act: 0.6361. Min Act: -0.0000

Data Index: 877114 (C4 (Web Text))

Max Activating Token Index: 785

Text #1

Max Range: 0.6778. Min Range: -0.6778

Max Act: 0.6313. Min Act: -0.0000

Data Index: 1365590 (Python Code)

Max Activating Token Index: 751

Text #2

Max Range: 0.6778. Min Range: -0.6778

Max Act: 0.6778. Min Act: -0.0000

Data Index: 726102 (C4 (Web Text))

Max Activating Token Index: 69

Text #3

Max Range: 0.6778. Min Range: -0.6778

Max Act: 0.6050. Min Act: -0.0000

Data Index: 886759 (C4 (Web Text))

Max Activating Token Index: 111

Text #4

Max Range: 0.6778. Min Range: -0.6778

Max Act: 0.5928. Min Act: -0.0000

Data Index: 393266 (C4 (Web Text))

Max Activating Token Index: 433

Text #5

Max Range: 0.6778. Min Range: -0.6778

Max Act: 0.5991. Min Act: -0.0000

Data Index: 1374430 (Python Code)

Max Activating Token Index: 430

Text #6

Max Range: 0.6778. Min Range: -0.6778

Max Act: 0.5601. Min Act: -0.0000

Data Index: 1487073 (Python Code)

Max Activating Token Index: 47

Text #7

Max Range: 0.6778. Min Range: -0.6778

Max Act: 0.5935. Min Act: -0.0000

Data Index: 1381475 (Python Code)

Max Activating Token Index: 589

Text #8

Max Range: 0.6778. Min Range: -0.6778

Max Act: 0.5511. Min Act: -0.0000

Data Index: 1349124 (C4 (Web Text))

Max Activating Token Index: 156

Text #9

Max Range: 0.6778. Min Range: -0.6778

Max Act: 0.5888. Min Act: -0.0000

Data Index: 953968 (C4 (Web Text))

Max Activating Token Index: 782

Text #10

Max Range: 0.6778. Min Range: -0.6778

Max Act: 0.5618. Min Act: -0.0000

Data Index: 716290 (C4 (Web Text))

Max Activating Token Index: 345

Text #11

Max Range: 0.6778. Min Range: -0.6778

Max Act: 0.5594. Min Act: -0.0000

Data Index: 887719 (C4 (Web Text))

Max Activating Token Index: 219

Text #12

Max Range: 0.6778. Min Range: -0.6778

Max Act: 0.5667. Min Act: -0.0000

Data Index: 748210 (C4 (Web Text))

Max Activating Token Index: 35

Text #13

Max Range: 0.6778. Min Range: -0.6778

Max Act: 0.5089. Min Act: -0.0000

Data Index: 199256 (C4 (Web Text))

Max Activating Token Index: 353

Text #14

Max Range: 0.6778. Min Range: -0.6778

Max Act: 0.5563. Min Act: -0.0000

Data Index: 1553344 (Python Code)

Max Activating Token Index: 605

Text #15

Max Range: 0.6778. Min Range: -0.6778

Max Act: 0.5208. Min Act: -0.0000

Data Index: 1494963 (Python Code)

Max Activating Token Index: 623

Text #16

Max Range: 0.6778. Min Range: -0.6778

Max Act: 0.5167. Min Act: -0.0000

Data Index: 1486307 (Python Code)

Max Activating Token Index: 658

Text #17

Max Range: 0.6778. Min Range: -0.6778

Max Act: 0.5191. Min Act: -0.0000

Data Index: 1575271 (Python Code)

Max Activating Token Index: 202

Text #18

Max Range: 0.6778. Min Range: -0.6778

Max Act: 0.4980. Min Act: -0.0000

Data Index: 1542913 (Python Code)

Max Activating Token Index: 451

Text #19

Max Range: 0.6778. Min Range: -0.6778

Max Act: 0.5136. Min Act: -0.0000

Data Index: 1366608 (Python Code)

Max Activating Token Index: 404