Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3030 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2543. Min Range: -0.2543

Max Act: 0.2543. Min Act: 0.0000

Data Index: 1471453 (Python Code)

Max Activating Token Index: 245

Text #1

Max Range: 0.2543. Min Range: -0.2543

Max Act: 0.2059. Min Act: -0.0000

Data Index: 1636234 (Python Code)

Max Activating Token Index: 67

Text #2

Max Range: 0.2543. Min Range: -0.2543

Max Act: 0.2094. Min Act: -0.0000

Data Index: 1415158 (Python Code)

Max Activating Token Index: 45

Text #3

Max Range: 0.2543. Min Range: -0.2543

Max Act: 0.2169. Min Act: -0.0000

Data Index: 1364669 (Python Code)

Max Activating Token Index: 162

Text #4

Max Range: 0.2543. Min Range: -0.2543

Max Act: 0.2029. Min Act: 0.0000

Data Index: 1549041 (Python Code)

Max Activating Token Index: 45

Text #5

Max Range: 0.2543. Min Range: -0.2543

Max Act: 0.2080. Min Act: 0.0001

Data Index: 1581025 (Python Code)

Max Activating Token Index: 418

Text #6

Max Range: 0.2543. Min Range: -0.2543

Max Act: 0.2067. Min Act: 0.0001

Data Index: 1362302 (Python Code)

Max Activating Token Index: 460

Text #7

Max Range: 0.2543. Min Range: -0.2543

Max Act: 0.1991. Min Act: 0.0000

Data Index: 1604215 (Python Code)

Max Activating Token Index: 645

Text #8

Max Range: 0.2543. Min Range: -0.2543

Max Act: 0.1974. Min Act: -0.0000

Data Index: 1504986 (Python Code)

Max Activating Token Index: 655

Text #9

Max Range: 0.2543. Min Range: -0.2543

Max Act: 0.1964. Min Act: 0.0001

Data Index: 1578761 (Python Code)

Max Activating Token Index: 128

Text #10

Max Range: 0.2543. Min Range: -0.2543

Max Act: 0.1898. Min Act: -0.0000

Data Index: 1554392 (Python Code)

Max Activating Token Index: 45

Text #11

Max Range: 0.2543. Min Range: -0.2543

Max Act: 0.1987. Min Act: 0.0001

Data Index: 1569346 (Python Code)

Max Activating Token Index: 321

Text #12

Max Range: 0.2543. Min Range: -0.2543

Max Act: 0.1860. Min Act: -0.0000

Data Index: 1389436 (Python Code)

Max Activating Token Index: 238

Text #13

Max Range: 0.2543. Min Range: -0.2543

Max Act: 0.1864. Min Act: -0.0000

Data Index: 1544522 (Python Code)

Max Activating Token Index: 240

Text #14

Max Range: 0.2543. Min Range: -0.2543

Max Act: 0.1740. Min Act: -0.0001

Data Index: 1584320 (Python Code)

Max Activating Token Index: 156

Text #15

Max Range: 0.2543. Min Range: -0.2543

Max Act: 0.1846. Min Act: -0.0000

Data Index: 1621876 (Python Code)

Max Activating Token Index: 8

Text #16

Max Range: 0.2543. Min Range: -0.2543

Max Act: 0.1879. Min Act: -0.0001

Data Index: 1476421 (Python Code)

Max Activating Token Index: 333

Text #17

Max Range: 0.2543. Min Range: -0.2543

Max Act: 0.1867. Min Act: 0.0000

Data Index: 1653768 (Python Code)

Max Activating Token Index: 373

Text #18

Max Range: 0.2543. Min Range: -0.2543

Max Act: 0.1775. Min Act: 0.0001

Data Index: 1609940 (Python Code)

Max Activating Token Index: 33

Text #19

Max Range: 0.2543. Min Range: -0.2543

Max Act: 0.1695. Min Act: -0.0000

Data Index: 1551495 (Python Code)

Max Activating Token Index: 512