Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4672 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.2122. Min Act: -0.0000

Data Index: 1582433 (Python Code)

Max Activating Token Index: 853

Text #1

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.2475. Min Act: -0.0000

Data Index: 1350004 (C4 (Web Text))

Max Activating Token Index: 113

Text #2

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.1922. Min Act: -0.0000

Data Index: 1429132 (Python Code)

Max Activating Token Index: 378

Text #3

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.1743. Min Act: -0.0000

Data Index: 1597035 (Python Code)

Max Activating Token Index: 803

Text #4

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.1757. Min Act: -0.0000

Data Index: 1428351 (Python Code)

Max Activating Token Index: 542

Text #5

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.1909. Min Act: -0.0000

Data Index: 343110 (C4 (Web Text))

Max Activating Token Index: 843

Text #6

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.1690. Min Act: -0.0000

Data Index: 960055 (C4 (Web Text))

Max Activating Token Index: 276

Text #7

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.1970. Min Act: -0.0000

Data Index: 1377822 (Python Code)

Max Activating Token Index: 826

Text #8

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.1897. Min Act: -0.0000

Data Index: 1538012 (Python Code)

Max Activating Token Index: 934

Text #9

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.1760. Min Act: -0.0000

Data Index: 1390300 (Python Code)

Max Activating Token Index: 55

Text #10

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.1519. Min Act: -0.0000

Data Index: 1505440 (Python Code)

Max Activating Token Index: 286

Text #11

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.1669. Min Act: -0.0000

Data Index: 1648103 (Python Code)

Max Activating Token Index: 53

Text #12

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.1558. Min Act: -0.0000

Data Index: 1494980 (Python Code)

Max Activating Token Index: 43

Text #13

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.1550. Min Act: -0.0000

Data Index: 871461 (C4 (Web Text))

Max Activating Token Index: 919

Text #14

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.1588. Min Act: -0.0000

Data Index: 1452402 (Python Code)

Max Activating Token Index: 58

Text #15

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.1656. Min Act: -0.0000

Data Index: 1405174 (Python Code)

Max Activating Token Index: 91

Text #16

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.1704. Min Act: -0.0000

Data Index: 1487896 (Python Code)

Max Activating Token Index: 69

Text #17

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.1479. Min Act: -0.0000

Data Index: 1466296 (Python Code)

Max Activating Token Index: 196

Text #18

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.1576. Min Act: -0.0000

Data Index: 1518908 (Python Code)

Max Activating Token Index: 119

Text #19

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.1627. Min Act: -0.0000

Data Index: 142333 (C4 (Web Text))

Max Activating Token Index: 126