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

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

Neuron 1990 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: 1.9606. Min Range: -1.9606

Max Act: 1.9606. Min Act: -0.0000

Data Index: 1360032 (Python Code)

Max Activating Token Index: 983

Text #1

Max Range: 1.9606. Min Range: -1.9606

Max Act: 1.8383. Min Act: -0.0000

Data Index: 1468741 (Python Code)

Max Activating Token Index: 690

Text #2

Max Range: 1.9606. Min Range: -1.9606

Max Act: 1.8100. Min Act: -0.0000

Data Index: 1532286 (Python Code)

Max Activating Token Index: 925

Text #3

Max Range: 1.9606. Min Range: -1.9606

Max Act: 1.7209. Min Act: -0.0000

Data Index: 1570680 (Python Code)

Max Activating Token Index: 492

Text #4

Max Range: 1.9606. Min Range: -1.9606

Max Act: 1.7624. Min Act: -0.0000

Data Index: 1441481 (Python Code)

Max Activating Token Index: 914

Text #5

Max Range: 1.9606. Min Range: -1.9606

Max Act: 1.6680. Min Act: -0.0000

Data Index: 1601055 (Python Code)

Max Activating Token Index: 960

Text #6

Max Range: 1.9606. Min Range: -1.9606

Max Act: 1.6983. Min Act: -0.0000

Data Index: 1561094 (Python Code)

Max Activating Token Index: 457

Text #7

Max Range: 1.9606. Min Range: -1.9606

Max Act: 1.6565. Min Act: -0.0000

Data Index: 1512375 (Python Code)

Max Activating Token Index: 398

Text #8

Max Range: 1.9606. Min Range: -1.9606

Max Act: 1.5901. Min Act: -0.0000

Data Index: 1385043 (Python Code)

Max Activating Token Index: 355

Text #9

Max Range: 1.9606. Min Range: -1.9606

Max Act: 1.7257. Min Act: -0.0000

Data Index: 1407694 (Python Code)

Max Activating Token Index: 158

Text #10

Max Range: 1.9606. Min Range: -1.9606

Max Act: 1.6666. Min Act: -0.0000

Data Index: 1381037 (Python Code)

Max Activating Token Index: 284

Text #11

Max Range: 1.9606. Min Range: -1.9606

Max Act: 1.7575. Min Act: -0.0000

Data Index: 1396976 (Python Code)

Max Activating Token Index: 343

Text #12

Max Range: 1.9606. Min Range: -1.9606

Max Act: 1.6483. Min Act: -0.0000

Data Index: 1632196 (Python Code)

Max Activating Token Index: 72

Text #13

Max Range: 1.9606. Min Range: -1.9606

Max Act: 1.6973. Min Act: -0.0000

Data Index: 1436128 (Python Code)

Max Activating Token Index: 65

Text #14

Max Range: 1.9606. Min Range: -1.9606

Max Act: 1.7466. Min Act: -0.0000

Data Index: 1578624 (Python Code)

Max Activating Token Index: 554

Text #15

Max Range: 1.9606. Min Range: -1.9606

Max Act: 1.6496. Min Act: -0.0000

Data Index: 1488520 (Python Code)

Max Activating Token Index: 740

Text #16

Max Range: 1.9606. Min Range: -1.9606

Max Act: 1.6059. Min Act: -0.0000

Data Index: 1608948 (Python Code)

Max Activating Token Index: 242

Text #17

Max Range: 1.9606. Min Range: -1.9606

Max Act: 1.5735. Min Act: -0.0000

Data Index: 1498372 (Python Code)

Max Activating Token Index: 52

Text #18

Max Range: 1.9606. Min Range: -1.9606

Max Act: 1.5698. Min Act: -0.0000

Data Index: 1467486 (Python Code)

Max Activating Token Index: 872

Text #19

Max Range: 1.9606. Min Range: -1.9606

Max Act: 1.6069. Min Act: -0.0000

Data Index: 1598646 (Python Code)

Max Activating Token Index: 572