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

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

Neuron 618 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2921. Min Range: -2.2921

Max Act: 2.2921. Min Act: -0.0000

Data Index: 1612439 (Python Code)

Max Activating Token Index: 739

Text #1

Max Range: 2.2921. Min Range: -2.2921

Max Act: 1.5080. Min Act: -0.0000

Data Index: 1424743 (Python Code)

Max Activating Token Index: 102

Text #2

Max Range: 2.2921. Min Range: -2.2921

Max Act: 1.5519. Min Act: -0.0000

Data Index: 1366528 (Python Code)

Max Activating Token Index: 574

Text #3

Max Range: 2.2921. Min Range: -2.2921

Max Act: 1.6221. Min Act: -0.0000

Data Index: 1456995 (Python Code)

Max Activating Token Index: 366

Text #4

Max Range: 2.2921. Min Range: -2.2921

Max Act: 1.4803. Min Act: -0.0000

Data Index: 1427794 (Python Code)

Max Activating Token Index: 393

Text #5

Max Range: 2.2921. Min Range: -2.2921

Max Act: 1.4176. Min Act: -0.0000

Data Index: 1500307 (Python Code)

Max Activating Token Index: 823

Text #6

Max Range: 2.2921. Min Range: -2.2921

Max Act: 1.5998. Min Act: -0.0000

Data Index: 1638111 (Python Code)

Max Activating Token Index: 940

Text #7

Max Range: 2.2921. Min Range: -2.2921

Max Act: 1.3999. Min Act: -0.0000

Data Index: 1366073 (Python Code)

Max Activating Token Index: 287

Text #8

Max Range: 2.2921. Min Range: -2.2921

Max Act: 1.3720. Min Act: -0.0000

Data Index: 1413024 (Python Code)

Max Activating Token Index: 458

Text #9

Max Range: 2.2921. Min Range: -2.2921

Max Act: 1.2512. Min Act: -0.0000

Data Index: 11004 (C4 (Web Text))

Max Activating Token Index: 60

Text #10

Max Range: 2.2921. Min Range: -2.2921

Max Act: 1.2366. Min Act: -0.0000

Data Index: 1194493 (C4 (Web Text))

Max Activating Token Index: 534

Text #11

Max Range: 2.2921. Min Range: -2.2921

Max Act: 1.2264. Min Act: -0.0000

Data Index: 1456332 (Python Code)

Max Activating Token Index: 665

Text #12

Max Range: 2.2921. Min Range: -2.2921

Max Act: 1.3199. Min Act: -0.0000

Data Index: 1590582 (Python Code)

Max Activating Token Index: 840

Text #13

Max Range: 2.2921. Min Range: -2.2921

Max Act: 1.2271. Min Act: -0.0000

Data Index: 1414528 (Python Code)

Max Activating Token Index: 656

Text #14

Max Range: 2.2921. Min Range: -2.2921

Max Act: 1.1706. Min Act: -0.0000

Data Index: 1566247 (Python Code)

Max Activating Token Index: 493

Text #15

Max Range: 2.2921. Min Range: -2.2921

Max Act: 1.3168. Min Act: -0.0000

Data Index: 1438459 (Python Code)

Max Activating Token Index: 1009

Text #16

Max Range: 2.2921. Min Range: -2.2921

Max Act: 1.1902. Min Act: -0.0000

Data Index: 316677 (C4 (Web Text))

Max Activating Token Index: 956

Text #17

Max Range: 2.2921. Min Range: -2.2921

Max Act: 1.1837. Min Act: -0.0000

Data Index: 1611727 (Python Code)

Max Activating Token Index: 650

Text #18

Max Range: 2.2921. Min Range: -2.2921

Max Act: 1.2506. Min Act: -0.0000

Data Index: 448469 (C4 (Web Text))

Max Activating Token Index: 402

Text #19

Max Range: 2.2921. Min Range: -2.2921

Max Act: 1.1000. Min Act: -0.0000

Data Index: 1370612 (Python Code)

Max Activating Token Index: 693