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

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

Neuron 4 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: 2.1642. Min Range: -2.1642

Max Act: 2.1642. Min Act: -0.0000

Data Index: 576262 (C4 (Web Text))

Max Activating Token Index: 593

Text #1

Max Range: 2.1642. Min Range: -2.1642

Max Act: 1.8114. Min Act: -0.0000

Data Index: 124718 (C4 (Web Text))

Max Activating Token Index: 63

Text #2

Max Range: 2.1642. Min Range: -2.1642

Max Act: 1.7116. Min Act: -0.0000

Data Index: 244142 (C4 (Web Text))

Max Activating Token Index: 968

Text #3

Max Range: 2.1642. Min Range: -2.1642

Max Act: 1.4363. Min Act: -0.0000

Data Index: 207064 (C4 (Web Text))

Max Activating Token Index: 62

Text #4

Max Range: 2.1642. Min Range: -2.1642

Max Act: 1.3651. Min Act: -0.0000

Data Index: 1474425 (Python Code)

Max Activating Token Index: 364

Text #5

Max Range: 2.1642. Min Range: -2.1642

Max Act: 1.3936. Min Act: -0.0000

Data Index: 1653220 (Python Code)

Max Activating Token Index: 285

Text #6

Max Range: 2.1642. Min Range: -2.1642

Max Act: 1.3360. Min Act: -0.0000

Data Index: 752423 (C4 (Web Text))

Max Activating Token Index: 489

Text #7

Max Range: 2.1642. Min Range: -2.1642

Max Act: 1.4611. Min Act: -0.0000

Data Index: 764540 (C4 (Web Text))

Max Activating Token Index: 464

Text #8

Max Range: 2.1642. Min Range: -2.1642

Max Act: 1.3242. Min Act: -0.0000

Data Index: 4550 (C4 (Web Text))

Max Activating Token Index: 37

Text #9

Max Range: 2.1642. Min Range: -2.1642

Max Act: 1.2366. Min Act: -0.0000

Data Index: 875328 (C4 (Web Text))

Max Activating Token Index: 249

Text #10

Max Range: 2.1642. Min Range: -2.1642

Max Act: 1.2141. Min Act: -0.0000

Data Index: 1348593 (C4 (Web Text))

Max Activating Token Index: 626

Text #11

Max Range: 2.1642. Min Range: -2.1642

Max Act: 1.2077. Min Act: -0.0000

Data Index: 781904 (C4 (Web Text))

Max Activating Token Index: 746

Text #12

Max Range: 2.1642. Min Range: -2.1642

Max Act: 1.1228. Min Act: -0.0000

Data Index: 1004620 (C4 (Web Text))

Max Activating Token Index: 159

Text #13

Max Range: 2.1642. Min Range: -2.1642

Max Act: 1.0561. Min Act: -0.0000

Data Index: 264382 (C4 (Web Text))

Max Activating Token Index: 789

Text #14

Max Range: 2.1642. Min Range: -2.1642

Max Act: 1.0883. Min Act: -0.0000

Data Index: 774949 (C4 (Web Text))

Max Activating Token Index: 170

Text #15

Max Range: 2.1642. Min Range: -2.1642

Max Act: 1.0897. Min Act: -0.0000

Data Index: 1617003 (Python Code)

Max Activating Token Index: 356

Text #16

Max Range: 2.1642. Min Range: -2.1642

Max Act: 1.0345. Min Act: -0.0000

Data Index: 1430820 (Python Code)

Max Activating Token Index: 30

Text #17

Max Range: 2.1642. Min Range: -2.1642

Max Act: 0.9613. Min Act: -0.0000

Data Index: 585110 (C4 (Web Text))

Max Activating Token Index: 976

Text #18

Max Range: 2.1642. Min Range: -2.1642

Max Act: 1.0116. Min Act: -0.0000

Data Index: 974702 (C4 (Web Text))

Max Activating Token Index: 738

Text #19

Max Range: 2.1642. Min Range: -2.1642

Max Act: 0.9324. Min Act: -0.0000

Data Index: 1110313 (C4 (Web Text))

Max Activating Token Index: 35