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

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

Neuron 3494 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7762. Min Range: -1.7762

Max Act: 1.7762. Min Act: -0.0000

Data Index: 1467998 (Python Code)

Max Activating Token Index: 531

Text #1

Max Range: 1.7762. Min Range: -1.7762

Max Act: 1.1863. Min Act: -0.0000

Data Index: 1598956 (Python Code)

Max Activating Token Index: 752

Text #2

Max Range: 1.7762. Min Range: -1.7762

Max Act: 1.0944. Min Act: -0.0000

Data Index: 1464587 (Python Code)

Max Activating Token Index: 600

Text #3

Max Range: 1.7762. Min Range: -1.7762

Max Act: 1.0404. Min Act: -0.0000

Data Index: 1619106 (Python Code)

Max Activating Token Index: 754

Text #4

Max Range: 1.7762. Min Range: -1.7762

Max Act: 1.0707. Min Act: -0.0000

Data Index: 1526341 (Python Code)

Max Activating Token Index: 674

Text #5

Max Range: 1.7762. Min Range: -1.7762

Max Act: 1.0124. Min Act: -0.0000

Data Index: 1442580 (Python Code)

Max Activating Token Index: 684

Text #6

Max Range: 1.7762. Min Range: -1.7762

Max Act: 1.0113. Min Act: -0.0000

Data Index: 1435713 (Python Code)

Max Activating Token Index: 439

Text #7

Max Range: 1.7762. Min Range: -1.7762

Max Act: 0.9013. Min Act: -0.0000

Data Index: 1549063 (Python Code)

Max Activating Token Index: 105

Text #8

Max Range: 1.7762. Min Range: -1.7762

Max Act: 0.8463. Min Act: -0.0000

Data Index: 1574634 (Python Code)

Max Activating Token Index: 189

Text #9

Max Range: 1.7762. Min Range: -1.7762

Max Act: 0.7728. Min Act: -0.0000

Data Index: 1410420 (Python Code)

Max Activating Token Index: 282

Text #10

Max Range: 1.7762. Min Range: -1.7762

Max Act: 0.7896. Min Act: -0.0000

Data Index: 1618227 (Python Code)

Max Activating Token Index: 317

Text #11

Max Range: 1.7762. Min Range: -1.7762

Max Act: 0.8108. Min Act: -0.0000

Data Index: 1485887 (Python Code)

Max Activating Token Index: 424

Text #12

Max Range: 1.7762. Min Range: -1.7762

Max Act: 0.7835. Min Act: -0.0000

Data Index: 1518218 (Python Code)

Max Activating Token Index: 357

Text #13

Max Range: 1.7762. Min Range: -1.7762

Max Act: 0.8621. Min Act: -0.0000

Data Index: 1437523 (Python Code)

Max Activating Token Index: 747

Text #14

Max Range: 1.7762. Min Range: -1.7762

Max Act: 0.7824. Min Act: -0.0000

Data Index: 1569732 (Python Code)

Max Activating Token Index: 50

Text #15

Max Range: 1.7762. Min Range: -1.7762

Max Act: 0.7349. Min Act: -0.0000

Data Index: 1617167 (Python Code)

Max Activating Token Index: 409

Text #16

Max Range: 1.7762. Min Range: -1.7762

Max Act: 0.7833. Min Act: -0.0000

Data Index: 1540166 (Python Code)

Max Activating Token Index: 585

Text #17

Max Range: 1.7762. Min Range: -1.7762

Max Act: 0.6956. Min Act: -0.0000

Data Index: 850136 (C4 (Web Text))

Max Activating Token Index: 592

Text #18

Max Range: 1.7762. Min Range: -1.7762

Max Act: 0.6757. Min Act: -0.0000

Data Index: 428077 (C4 (Web Text))

Max Activating Token Index: 561

Text #19

Max Range: 1.7762. Min Range: -1.7762

Max Act: 0.6175. Min Act: -0.0000

Data Index: 390273 (C4 (Web Text))

Max Activating Token Index: 309