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

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

Neuron 1361 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1984. Min Range: -2.1984

Max Act: 2.1984. Min Act: -0.0000

Data Index: 1438190 (Python Code)

Max Activating Token Index: 449

Text #1

Max Range: 2.1984. Min Range: -2.1984

Max Act: 1.8569. Min Act: -0.0000

Data Index: 1539916 (Python Code)

Max Activating Token Index: 341

Text #2

Max Range: 2.1984. Min Range: -2.1984

Max Act: 1.6760. Min Act: -0.0000

Data Index: 1641632 (Python Code)

Max Activating Token Index: 248

Text #3

Max Range: 2.1984. Min Range: -2.1984

Max Act: 1.7417. Min Act: -0.0000

Data Index: 1365508 (Python Code)

Max Activating Token Index: 966

Text #4

Max Range: 2.1984. Min Range: -2.1984

Max Act: 1.6298. Min Act: -0.0000

Data Index: 1540893 (Python Code)

Max Activating Token Index: 56

Text #5

Max Range: 2.1984. Min Range: -2.1984

Max Act: 1.5586. Min Act: -0.0000

Data Index: 1367794 (Python Code)

Max Activating Token Index: 744

Text #6

Max Range: 2.1984. Min Range: -2.1984

Max Act: 1.6580. Min Act: -0.0000

Data Index: 1366791 (Python Code)

Max Activating Token Index: 623

Text #7

Max Range: 2.1984. Min Range: -2.1984

Max Act: 1.5643. Min Act: -0.0000

Data Index: 1650738 (Python Code)

Max Activating Token Index: 305

Text #8

Max Range: 2.1984. Min Range: -2.1984

Max Act: 1.5615. Min Act: -0.0000

Data Index: 1464221 (Python Code)

Max Activating Token Index: 926

Text #9

Max Range: 2.1984. Min Range: -2.1984

Max Act: 1.5827. Min Act: -0.0000

Data Index: 1606908 (Python Code)

Max Activating Token Index: 366

Text #10

Max Range: 2.1984. Min Range: -2.1984

Max Act: 1.5040. Min Act: -0.0000

Data Index: 1625875 (Python Code)

Max Activating Token Index: 578

Text #11

Max Range: 2.1984. Min Range: -2.1984

Max Act: 1.4526. Min Act: -0.0000

Data Index: 1472809 (Python Code)

Max Activating Token Index: 862

Text #12

Max Range: 2.1984. Min Range: -2.1984

Max Act: 1.5699. Min Act: -0.0000

Data Index: 1365117 (Python Code)

Max Activating Token Index: 59

Text #13

Max Range: 2.1984. Min Range: -2.1984

Max Act: 1.5297. Min Act: -0.0000

Data Index: 1412155 (Python Code)

Max Activating Token Index: 780

Text #14

Max Range: 2.1984. Min Range: -2.1984

Max Act: 1.5179. Min Act: -0.0000

Data Index: 1469766 (Python Code)

Max Activating Token Index: 939

Text #15

Max Range: 2.1984. Min Range: -2.1984

Max Act: 1.4988. Min Act: -0.0000

Data Index: 1599905 (Python Code)

Max Activating Token Index: 571

Text #16

Max Range: 2.1984. Min Range: -2.1984

Max Act: 1.4431. Min Act: -0.0000

Data Index: 1410330 (Python Code)

Max Activating Token Index: 135

Text #17

Max Range: 2.1984. Min Range: -2.1984

Max Act: 1.4446. Min Act: -0.0000

Data Index: 1556124 (Python Code)

Max Activating Token Index: 98

Text #18

Max Range: 2.1984. Min Range: -2.1984

Max Act: 1.4641. Min Act: -0.0000

Data Index: 1363882 (Python Code)

Max Activating Token Index: 448

Text #19

Max Range: 2.1984. Min Range: -2.1984

Max Act: 1.4354. Min Act: -0.0000

Data Index: 1393070 (Python Code)

Max Activating Token Index: 940