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

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

Neuron 7 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5263. Min Range: -1.5263

Max Act: 1.5263. Min Act: -0.0000

Data Index: 1607121 (Python Code)

Max Activating Token Index: 804

Text #1

Max Range: 1.5263. Min Range: -1.5263

Max Act: 1.2371. Min Act: -0.0000

Data Index: 1400874 (Python Code)

Max Activating Token Index: 222

Text #2

Max Range: 1.5263. Min Range: -1.5263

Max Act: 1.1960. Min Act: -0.0000

Data Index: 1601647 (Python Code)

Max Activating Token Index: 16

Text #3

Max Range: 1.5263. Min Range: -1.5263

Max Act: 1.1836. Min Act: -0.0000

Data Index: 1412384 (Python Code)

Max Activating Token Index: 675

Text #4

Max Range: 1.5263. Min Range: -1.5263

Max Act: 1.0106. Min Act: -0.0000

Data Index: 1514159 (Python Code)

Max Activating Token Index: 111

Text #5

Max Range: 1.5263. Min Range: -1.5263

Max Act: 1.1480. Min Act: -0.0000

Data Index: 1486442 (Python Code)

Max Activating Token Index: 804

Text #6

Max Range: 1.5263. Min Range: -1.5263

Max Act: 1.0217. Min Act: -0.0000

Data Index: 1407530 (Python Code)

Max Activating Token Index: 996

Text #7

Max Range: 1.5263. Min Range: -1.5263

Max Act: 1.0755. Min Act: -0.0000

Data Index: 1533786 (Python Code)

Max Activating Token Index: 838

Text #8

Max Range: 1.5263. Min Range: -1.5263

Max Act: 1.0662. Min Act: -0.0000

Data Index: 1635445 (Python Code)

Max Activating Token Index: 347

Text #9

Max Range: 1.5263. Min Range: -1.5263

Max Act: 1.0177. Min Act: -0.0000

Data Index: 1516852 (Python Code)

Max Activating Token Index: 520

Text #10

Max Range: 1.5263. Min Range: -1.5263

Max Act: 1.0753. Min Act: -0.0000

Data Index: 1414187 (Python Code)

Max Activating Token Index: 7

Text #11

Max Range: 1.5263. Min Range: -1.5263

Max Act: 1.0611. Min Act: -0.0000

Data Index: 1417665 (Python Code)

Max Activating Token Index: 134

Text #12

Max Range: 1.5263. Min Range: -1.5263

Max Act: 1.0448. Min Act: 0.0001

Data Index: 1468159 (Python Code)

Max Activating Token Index: 543

Text #13

Max Range: 1.5263. Min Range: -1.5263

Max Act: 0.9957. Min Act: -0.0000

Data Index: 1603819 (Python Code)

Max Activating Token Index: 8

Text #14

Max Range: 1.5263. Min Range: -1.5263

Max Act: 0.9767. Min Act: -0.0000

Data Index: 1598088 (Python Code)

Max Activating Token Index: 523

Text #15

Max Range: 1.5263. Min Range: -1.5263

Max Act: 0.9092. Min Act: -0.0000

Data Index: 1607686 (Python Code)

Max Activating Token Index: 847

Text #16

Max Range: 1.5263. Min Range: -1.5263

Max Act: 0.9740. Min Act: -0.0000

Data Index: 1400684 (Python Code)

Max Activating Token Index: 473

Text #17

Max Range: 1.5263. Min Range: -1.5263

Max Act: 0.9587. Min Act: -0.0000

Data Index: 1634827 (Python Code)

Max Activating Token Index: 754

Text #18

Max Range: 1.5263. Min Range: -1.5263

Max Act: 0.8728. Min Act: -0.0000

Data Index: 1622918 (Python Code)

Max Activating Token Index: 665

Text #19

Max Range: 1.5263. Min Range: -1.5263

Max Act: 0.9755. Min Act: -0.0000

Data Index: 1602927 (Python Code)

Max Activating Token Index: 622