Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2979 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6892. Min Range: -0.6892

Max Act: 0.6892. Min Act: -0.0000

Data Index: 1531536 (Python Code)

Max Activating Token Index: 615

Text #1

Max Range: 0.6892. Min Range: -0.6892

Max Act: 0.6706. Min Act: -0.0000

Data Index: 1519412 (Python Code)

Max Activating Token Index: 335

Text #2

Max Range: 0.6892. Min Range: -0.6892

Max Act: 0.5689. Min Act: -0.0000

Data Index: 1653255 (Python Code)

Max Activating Token Index: 75

Text #3

Max Range: 0.6892. Min Range: -0.6892

Max Act: 0.6232. Min Act: -0.0000

Data Index: 1430541 (Python Code)

Max Activating Token Index: 463

Text #4

Max Range: 0.6892. Min Range: -0.6892

Max Act: 0.6534. Min Act: -0.0000

Data Index: 1466423 (Python Code)

Max Activating Token Index: 291

Text #5

Max Range: 0.6892. Min Range: -0.6892

Max Act: 0.5995. Min Act: -0.0000

Data Index: 1391272 (Python Code)

Max Activating Token Index: 376

Text #6

Max Range: 0.6892. Min Range: -0.6892

Max Act: 0.5970. Min Act: -0.0000

Data Index: 1395070 (Python Code)

Max Activating Token Index: 368

Text #7

Max Range: 0.6892. Min Range: -0.6892

Max Act: 0.6300. Min Act: -0.0000

Data Index: 1621693 (Python Code)

Max Activating Token Index: 106

Text #8

Max Range: 0.6892. Min Range: -0.6892

Max Act: 0.5675. Min Act: -0.0000

Data Index: 1619487 (Python Code)

Max Activating Token Index: 284

Text #9

Max Range: 0.6892. Min Range: -0.6892

Max Act: 0.5670. Min Act: -0.0000

Data Index: 1384373 (Python Code)

Max Activating Token Index: 166

Text #10

Max Range: 0.6892. Min Range: -0.6892

Max Act: 0.6178. Min Act: -0.0000

Data Index: 1533907 (Python Code)

Max Activating Token Index: 98

Text #11

Max Range: 0.6892. Min Range: -0.6892

Max Act: 0.5756. Min Act: -0.0000

Data Index: 1489623 (Python Code)

Max Activating Token Index: 703

Text #12

Max Range: 0.6892. Min Range: -0.6892

Max Act: 0.5736. Min Act: -0.0000

Data Index: 1395219 (Python Code)

Max Activating Token Index: 730

Text #13

Max Range: 0.6892. Min Range: -0.6892

Max Act: 0.5740. Min Act: -0.0000

Data Index: 1558242 (Python Code)

Max Activating Token Index: 146

Text #14

Max Range: 0.6892. Min Range: -0.6892

Max Act: 0.5688. Min Act: -0.0000

Data Index: 1465123 (Python Code)

Max Activating Token Index: 1017

Text #15

Max Range: 0.6892. Min Range: -0.6892

Max Act: 0.5488. Min Act: -0.0000

Data Index: 1064265 (C4 (Web Text))

Max Activating Token Index: 875

Text #16

Max Range: 0.6892. Min Range: -0.6892

Max Act: 0.5805. Min Act: -0.0000

Data Index: 1420310 (Python Code)

Max Activating Token Index: 444

Text #17

Max Range: 0.6892. Min Range: -0.6892

Max Act: 0.5353. Min Act: -0.0000

Data Index: 1598860 (Python Code)

Max Activating Token Index: 818

Text #18

Max Range: 0.6892. Min Range: -0.6892

Max Act: 0.5530. Min Act: -0.0000

Data Index: 1524899 (Python Code)

Max Activating Token Index: 91

Text #19

Max Range: 0.6892. Min Range: -0.6892

Max Act: 0.5247. Min Act: -0.0000

Data Index: 1557708 (Python Code)

Max Activating Token Index: 283