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

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

Neuron 2636 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4218. Min Range: -1.4218

Max Act: 1.4218. Min Act: -0.0000

Data Index: 1535129 (Python Code)

Max Activating Token Index: 334

Text #1

Max Range: 1.4218. Min Range: -1.4218

Max Act: 1.4025. Min Act: -0.0000

Data Index: 1426213 (Python Code)

Max Activating Token Index: 70

Text #2

Max Range: 1.4218. Min Range: -1.4218

Max Act: 1.2682. Min Act: -0.0000

Data Index: 1611124 (Python Code)

Max Activating Token Index: 3

Text #3

Max Range: 1.4218. Min Range: -1.4218

Max Act: 1.1944. Min Act: -0.0000

Data Index: 1411556 (Python Code)

Max Activating Token Index: 658

Text #4

Max Range: 1.4218. Min Range: -1.4218

Max Act: 1.1960. Min Act: -0.0000

Data Index: 1405106 (Python Code)

Max Activating Token Index: 476

Text #5

Max Range: 1.4218. Min Range: -1.4218

Max Act: 1.1909. Min Act: -0.0000

Data Index: 1466490 (Python Code)

Max Activating Token Index: 199

Text #6

Max Range: 1.4218. Min Range: -1.4218

Max Act: 1.1334. Min Act: -0.0000

Data Index: 1523204 (Python Code)

Max Activating Token Index: 1001

Text #7

Max Range: 1.4218. Min Range: -1.4218

Max Act: 1.0888. Min Act: -0.0000

Data Index: 1494486 (Python Code)

Max Activating Token Index: 914

Text #8

Max Range: 1.4218. Min Range: -1.4218

Max Act: 1.2322. Min Act: -0.0000

Data Index: 1479975 (Python Code)

Max Activating Token Index: 285

Text #9

Max Range: 1.4218. Min Range: -1.4218

Max Act: 1.1873. Min Act: -0.0000

Data Index: 1652177 (Python Code)

Max Activating Token Index: 902

Text #10

Max Range: 1.4218. Min Range: -1.4218

Max Act: 1.1423. Min Act: -0.0000

Data Index: 1397339 (Python Code)

Max Activating Token Index: 103

Text #11

Max Range: 1.4218. Min Range: -1.4218

Max Act: 1.1717. Min Act: -0.0000

Data Index: 1626959 (Python Code)

Max Activating Token Index: 32

Text #12

Max Range: 1.4218. Min Range: -1.4218

Max Act: 1.1254. Min Act: -0.0000

Data Index: 1425095 (Python Code)

Max Activating Token Index: 89

Text #13

Max Range: 1.4218. Min Range: -1.4218

Max Act: 1.1552. Min Act: -0.0000

Data Index: 1617457 (Python Code)

Max Activating Token Index: 73

Text #14

Max Range: 1.4218. Min Range: -1.4218

Max Act: 1.1183. Min Act: -0.0000

Data Index: 1369305 (Python Code)

Max Activating Token Index: 437

Text #15

Max Range: 1.4218. Min Range: -1.4218

Max Act: 1.1338. Min Act: -0.0000

Data Index: 1613889 (Python Code)

Max Activating Token Index: 1010

Text #16

Max Range: 1.4218. Min Range: -1.4218

Max Act: 0.9928. Min Act: -0.0000

Data Index: 1476321 (Python Code)

Max Activating Token Index: 787

Text #17

Max Range: 1.4218. Min Range: -1.4218

Max Act: 1.0842. Min Act: -0.0000

Data Index: 1601867 (Python Code)

Max Activating Token Index: 745

Text #18

Max Range: 1.4218. Min Range: -1.4218

Max Act: 0.9783. Min Act: 0.0000

Data Index: 1564695 (Python Code)

Max Activating Token Index: 915

Text #19

Max Range: 1.4218. Min Range: -1.4218

Max Act: 1.0567. Min Act: -0.0000

Data Index: 1453271 (Python Code)

Max Activating Token Index: 1003