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

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

Neuron 2718 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: 0.6928. Min Range: -0.6928

Max Act: 0.6928. Min Act: -0.0000

Data Index: 1424641 (Python Code)

Max Activating Token Index: 663

Text #1

Max Range: 0.6928. Min Range: -0.6928

Max Act: 0.6632. Min Act: -0.0000

Data Index: 1631700 (Python Code)

Max Activating Token Index: 990

Text #2

Max Range: 0.6928. Min Range: -0.6928

Max Act: 0.5929. Min Act: -0.0000

Data Index: 1622445 (Python Code)

Max Activating Token Index: 899

Text #3

Max Range: 0.6928. Min Range: -0.6928

Max Act: 0.5791. Min Act: -0.0000

Data Index: 1523103 (Python Code)

Max Activating Token Index: 861

Text #4

Max Range: 0.6928. Min Range: -0.6928

Max Act: 0.5765. Min Act: -0.0000

Data Index: 1507632 (Python Code)

Max Activating Token Index: 803

Text #5

Max Range: 0.6928. Min Range: -0.6928

Max Act: 0.5759. Min Act: -0.0000

Data Index: 1423785 (Python Code)

Max Activating Token Index: 175

Text #6

Max Range: 0.6928. Min Range: -0.6928

Max Act: 0.5373. Min Act: -0.0000

Data Index: 1656416 (Python Code)

Max Activating Token Index: 908

Text #7

Max Range: 0.6928. Min Range: -0.6928

Max Act: 0.5468. Min Act: -0.0000

Data Index: 1637098 (Python Code)

Max Activating Token Index: 1017

Text #8

Max Range: 0.6928. Min Range: -0.6928

Max Act: 0.5842. Min Act: -0.0000

Data Index: 1372325 (Python Code)

Max Activating Token Index: 843

Text #9

Max Range: 0.6928. Min Range: -0.6928

Max Act: 0.5224. Min Act: -0.0000

Data Index: 1651486 (Python Code)

Max Activating Token Index: 358

Text #10

Max Range: 0.6928. Min Range: -0.6928

Max Act: 0.5416. Min Act: -0.0000

Data Index: 1640417 (Python Code)

Max Activating Token Index: 965

Text #11

Max Range: 0.6928. Min Range: -0.6928

Max Act: 0.4512. Min Act: -0.0000

Data Index: 1635724 (Python Code)

Max Activating Token Index: 638

Text #12

Max Range: 0.6928. Min Range: -0.6928

Max Act: 0.5370. Min Act: -0.0000

Data Index: 1529418 (Python Code)

Max Activating Token Index: 940

Text #13

Max Range: 0.6928. Min Range: -0.6928

Max Act: 0.5325. Min Act: -0.0000

Data Index: 1579839 (Python Code)

Max Activating Token Index: 239

Text #14

Max Range: 0.6928. Min Range: -0.6928

Max Act: 0.5109. Min Act: -0.0000

Data Index: 1493169 (Python Code)

Max Activating Token Index: 887

Text #15

Max Range: 0.6928. Min Range: -0.6928

Max Act: 0.5467. Min Act: -0.0000

Data Index: 1368163 (Python Code)

Max Activating Token Index: 883

Text #16

Max Range: 0.6928. Min Range: -0.6928

Max Act: 0.5385. Min Act: -0.0000

Data Index: 1472409 (Python Code)

Max Activating Token Index: 911

Text #17

Max Range: 0.6928. Min Range: -0.6928

Max Act: 0.5785. Min Act: -0.0000

Data Index: 1506609 (Python Code)

Max Activating Token Index: 893

Text #18

Max Range: 0.6928. Min Range: -0.6928

Max Act: 0.5214. Min Act: -0.0000

Data Index: 1433043 (Python Code)

Max Activating Token Index: 401

Text #19

Max Range: 0.6928. Min Range: -0.6928

Max Act: 0.5183. Min Act: -0.0000

Data Index: 1456989 (Python Code)

Max Activating Token Index: 639