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

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

Neuron 4001 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.6840. Min Range: -1.6840

Max Act: 1.6840. Min Act: -0.0000

Data Index: 1522534 (Python Code)

Max Activating Token Index: 929

Text #1

Max Range: 1.6840. Min Range: -1.6840

Max Act: 1.6618. Min Act: -0.0000

Data Index: 1223727 (C4 (Web Text))

Max Activating Token Index: 124

Text #2

Max Range: 1.6840. Min Range: -1.6840

Max Act: 1.6380. Min Act: -0.0000

Data Index: 1545764 (Python Code)

Max Activating Token Index: 1021

Text #3

Max Range: 1.6840. Min Range: -1.6840

Max Act: 1.6193. Min Act: -0.0000

Data Index: 1407455 (Python Code)

Max Activating Token Index: 873

Text #4

Max Range: 1.6840. Min Range: -1.6840

Max Act: 1.5580. Min Act: -0.0000

Data Index: 1597451 (Python Code)

Max Activating Token Index: 925

Text #5

Max Range: 1.6840. Min Range: -1.6840

Max Act: 1.5477. Min Act: -0.0000

Data Index: 1635676 (Python Code)

Max Activating Token Index: 969

Text #6

Max Range: 1.6840. Min Range: -1.6840

Max Act: 1.5806. Min Act: -0.0000

Data Index: 604593 (C4 (Web Text))

Max Activating Token Index: 710

Text #7

Max Range: 1.6840. Min Range: -1.6840

Max Act: 1.5567. Min Act: -0.0000

Data Index: 91258 (C4 (Web Text))

Max Activating Token Index: 873

Text #8

Max Range: 1.6840. Min Range: -1.6840

Max Act: 1.5482. Min Act: -0.0000

Data Index: 1113004 (C4 (Web Text))

Max Activating Token Index: 826

Text #9

Max Range: 1.6840. Min Range: -1.6840

Max Act: 1.4596. Min Act: -0.0000

Data Index: 418265 (C4 (Web Text))

Max Activating Token Index: 83

Text #10

Max Range: 1.6840. Min Range: -1.6840

Max Act: 1.5285. Min Act: -0.0000

Data Index: 1505077 (Python Code)

Max Activating Token Index: 60

Text #11

Max Range: 1.6840. Min Range: -1.6840

Max Act: 1.5264. Min Act: -0.0000

Data Index: 1535786 (Python Code)

Max Activating Token Index: 561

Text #12

Max Range: 1.6840. Min Range: -1.6840

Max Act: 1.5116. Min Act: -0.0000

Data Index: 1516867 (Python Code)

Max Activating Token Index: 852

Text #13

Max Range: 1.6840. Min Range: -1.6840

Max Act: 1.5182. Min Act: -0.0000

Data Index: 53007 (C4 (Web Text))

Max Activating Token Index: 182

Text #14

Max Range: 1.6840. Min Range: -1.6840

Max Act: 1.6077. Min Act: -0.0000

Data Index: 1479510 (Python Code)

Max Activating Token Index: 323

Text #15

Max Range: 1.6840. Min Range: -1.6840

Max Act: 1.5154. Min Act: -0.0000

Data Index: 1167040 (C4 (Web Text))

Max Activating Token Index: 650

Text #16

Max Range: 1.6840. Min Range: -1.6840

Max Act: 1.6023. Min Act: -0.0000

Data Index: 1418194 (Python Code)

Max Activating Token Index: 487

Text #17

Max Range: 1.6840. Min Range: -1.6840

Max Act: 1.5543. Min Act: -0.0000

Data Index: 1551510 (Python Code)

Max Activating Token Index: 929

Text #18

Max Range: 1.6840. Min Range: -1.6840

Max Act: 1.5025. Min Act: -0.0000

Data Index: 1400360 (Python Code)

Max Activating Token Index: 142

Text #19

Max Range: 1.6840. Min Range: -1.6840

Max Act: 1.4899. Min Act: -0.0000

Data Index: 1616816 (Python Code)

Max Activating Token Index: 643