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

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

Neuron 4694 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: 2.4992. Min Range: -2.4992

Max Act: 2.4992. Min Act: -0.0000

Data Index: 1424428 (Python Code)

Max Activating Token Index: 202

Text #1

Max Range: 2.4992. Min Range: -2.4992

Max Act: 2.3220. Min Act: -0.0000

Data Index: 1361673 (Python Code)

Max Activating Token Index: 168

Text #2

Max Range: 2.4992. Min Range: -2.4992

Max Act: 2.1710. Min Act: -0.0000

Data Index: 1615432 (Python Code)

Max Activating Token Index: 124

Text #3

Max Range: 2.4992. Min Range: -2.4992

Max Act: 2.1302. Min Act: -0.0000

Data Index: 1458840 (Python Code)

Max Activating Token Index: 327

Text #4

Max Range: 2.4992. Min Range: -2.4992

Max Act: 1.8562. Min Act: -0.0000

Data Index: 1421859 (Python Code)

Max Activating Token Index: 754

Text #5

Max Range: 2.4992. Min Range: -2.4992

Max Act: 1.7733. Min Act: -0.0000

Data Index: 19938 (C4 (Web Text))

Max Activating Token Index: 373

Text #6

Max Range: 2.4992. Min Range: -2.4992

Max Act: 1.8778. Min Act: -0.0000

Data Index: 230492 (C4 (Web Text))

Max Activating Token Index: 308

Text #7

Max Range: 2.4992. Min Range: -2.4992

Max Act: 1.9477. Min Act: -0.0000

Data Index: 1070451 (C4 (Web Text))

Max Activating Token Index: 24

Text #8

Max Range: 2.4992. Min Range: -2.4992

Max Act: 2.0039. Min Act: -0.0000

Data Index: 760469 (C4 (Web Text))

Max Activating Token Index: 321

Text #9

Max Range: 2.4992. Min Range: -2.4992

Max Act: 1.8972. Min Act: -0.0000

Data Index: 1602331 (Python Code)

Max Activating Token Index: 428

Text #10

Max Range: 2.4992. Min Range: -2.4992

Max Act: 1.8999. Min Act: -0.0000

Data Index: 1250542 (C4 (Web Text))

Max Activating Token Index: 390

Text #11

Max Range: 2.4992. Min Range: -2.4992

Max Act: 1.9014. Min Act: -0.0000

Data Index: 1546617 (Python Code)

Max Activating Token Index: 437

Text #12

Max Range: 2.4992. Min Range: -2.4992

Max Act: 1.8521. Min Act: -0.0000

Data Index: 1580214 (Python Code)

Max Activating Token Index: 354

Text #13

Max Range: 2.4992. Min Range: -2.4992

Max Act: 1.8662. Min Act: -0.0000

Data Index: 174427 (C4 (Web Text))

Max Activating Token Index: 75

Text #14

Max Range: 2.4992. Min Range: -2.4992

Max Act: 1.7377. Min Act: -0.0000

Data Index: 576472 (C4 (Web Text))

Max Activating Token Index: 39

Text #15

Max Range: 2.4992. Min Range: -2.4992

Max Act: 1.9302. Min Act: -0.0000

Data Index: 1649799 (Python Code)

Max Activating Token Index: 970

Text #16

Max Range: 2.4992. Min Range: -2.4992

Max Act: 2.0362. Min Act: -0.0000

Data Index: 481337 (C4 (Web Text))

Max Activating Token Index: 324

Text #17

Max Range: 2.4992. Min Range: -2.4992

Max Act: 1.7512. Min Act: -0.0000

Data Index: 822895 (C4 (Web Text))

Max Activating Token Index: 619

Text #18

Max Range: 2.4992. Min Range: -2.4992

Max Act: 1.7731. Min Act: -0.0000

Data Index: 1042618 (C4 (Web Text))

Max Activating Token Index: 680

Text #19

Max Range: 2.4992. Min Range: -2.4992

Max Act: 1.7626. Min Act: -0.0000

Data Index: 1026129 (C4 (Web Text))

Max Activating Token Index: 29