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

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

Neuron 862 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.5972. Min Range: -4.5972

Max Act: 4.5972. Min Act: -0.0000

Data Index: 1583232 (Python Code)

Max Activating Token Index: 730

Text #1

Max Range: 4.5972. Min Range: -4.5972

Max Act: 4.2744. Min Act: -0.0000

Data Index: 1385132 (Python Code)

Max Activating Token Index: 263

Text #2

Max Range: 4.5972. Min Range: -4.5972

Max Act: 4.1586. Min Act: -0.0000

Data Index: 1655790 (Python Code)

Max Activating Token Index: 265

Text #3

Max Range: 4.5972. Min Range: -4.5972

Max Act: 4.1661. Min Act: -0.0000

Data Index: 1364358 (Python Code)

Max Activating Token Index: 441

Text #4

Max Range: 4.5972. Min Range: -4.5972

Max Act: 3.5651. Min Act: -0.0000

Data Index: 1507841 (Python Code)

Max Activating Token Index: 231

Text #5

Max Range: 4.5972. Min Range: -4.5972

Max Act: 3.8876. Min Act: -0.0000

Data Index: 1524707 (Python Code)

Max Activating Token Index: 59

Text #6

Max Range: 4.5972. Min Range: -4.5972

Max Act: 3.4065. Min Act: -0.0000

Data Index: 1548218 (Python Code)

Max Activating Token Index: 84

Text #7

Max Range: 4.5972. Min Range: -4.5972

Max Act: 3.8792. Min Act: -0.0000

Data Index: 1364014 (Python Code)

Max Activating Token Index: 361

Text #8

Max Range: 4.5972. Min Range: -4.5972

Max Act: 2.8754. Min Act: -0.0000

Data Index: 1634110 (Python Code)

Max Activating Token Index: 41

Text #9

Max Range: 4.5972. Min Range: -4.5972

Max Act: 2.7155. Min Act: -0.0000

Data Index: 1454628 (Python Code)

Max Activating Token Index: 689

Text #10

Max Range: 4.5972. Min Range: -4.5972

Max Act: 2.2240. Min Act: -0.0000

Data Index: 1629673 (Python Code)

Max Activating Token Index: 703

Text #11

Max Range: 4.5972. Min Range: -4.5972

Max Act: 0.1066. Min Act: -0.0000

Data Index: 1599078 (Python Code)

Max Activating Token Index: 375

Text #12

Max Range: 4.5972. Min Range: -4.5972

Max Act: 0.1058. Min Act: -0.0001

Data Index: 1650861 (Python Code)

Max Activating Token Index: 341

Text #13

Max Range: 4.5972. Min Range: -4.5972

Max Act: 0.0996. Min Act: -0.0001

Data Index: 1428413 (Python Code)

Max Activating Token Index: 490

Text #14

Max Range: 4.5972. Min Range: -4.5972

Max Act: 0.0690. Min Act: -0.0000

Data Index: 1510362 (Python Code)

Max Activating Token Index: 330

Text #15

Max Range: 4.5972. Min Range: -4.5972

Max Act: 0.0626. Min Act: -0.0000

Data Index: 1379890 (Python Code)

Max Activating Token Index: 478

Text #16

Max Range: 4.5972. Min Range: -4.5972

Max Act: 0.0703. Min Act: -0.0000

Data Index: 1420558 (Python Code)

Max Activating Token Index: 349

Text #17

Max Range: 4.5972. Min Range: -4.5972

Max Act: 0.0410. Min Act: -0.0000

Data Index: 1414340 (Python Code)

Max Activating Token Index: 292

Text #18

Max Range: 4.5972. Min Range: -4.5972

Max Act: 0.0542. Min Act: -0.0000

Data Index: 1544811 (Python Code)

Max Activating Token Index: 21

Text #19

Max Range: 4.5972. Min Range: -4.5972

Max Act: 0.0585. Min Act: -0.0000

Data Index: 1598472 (Python Code)

Max Activating Token Index: 801