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

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

Neuron 1431 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8042. Min Range: -1.8042

Max Act: 1.8042. Min Act: -0.0000

Data Index: 1576525 (Python Code)

Max Activating Token Index: 145

Text #1

Max Range: 1.8042. Min Range: -1.8042

Max Act: 1.5890. Min Act: -0.0000

Data Index: 1494978 (Python Code)

Max Activating Token Index: 273

Text #2

Max Range: 1.8042. Min Range: -1.8042

Max Act: 1.4106. Min Act: -0.0000

Data Index: 1534198 (Python Code)

Max Activating Token Index: 280

Text #3

Max Range: 1.8042. Min Range: -1.8042

Max Act: 1.5679. Min Act: -0.0000

Data Index: 1444455 (Python Code)

Max Activating Token Index: 65

Text #4

Max Range: 1.8042. Min Range: -1.8042

Max Act: 1.5041. Min Act: -0.0000

Data Index: 1406384 (Python Code)

Max Activating Token Index: 505

Text #5

Max Range: 1.8042. Min Range: -1.8042

Max Act: 1.4762. Min Act: -0.0000

Data Index: 1553095 (Python Code)

Max Activating Token Index: 113

Text #6

Max Range: 1.8042. Min Range: -1.8042

Max Act: 1.4884. Min Act: -0.0000

Data Index: 1615084 (Python Code)

Max Activating Token Index: 746

Text #7

Max Range: 1.8042. Min Range: -1.8042

Max Act: 1.4512. Min Act: -0.0000

Data Index: 1447682 (Python Code)

Max Activating Token Index: 145

Text #8

Max Range: 1.8042. Min Range: -1.8042

Max Act: 1.3873. Min Act: -0.0000

Data Index: 1627281 (Python Code)

Max Activating Token Index: 751

Text #9

Max Range: 1.8042. Min Range: -1.8042

Max Act: 1.3622. Min Act: -0.0000

Data Index: 1614078 (Python Code)

Max Activating Token Index: 213

Text #10

Max Range: 1.8042. Min Range: -1.8042

Max Act: 1.4172. Min Act: -0.0000

Data Index: 1569695 (Python Code)

Max Activating Token Index: 433

Text #11

Max Range: 1.8042. Min Range: -1.8042

Max Act: 1.3952. Min Act: -0.0000

Data Index: 1582669 (Python Code)

Max Activating Token Index: 105

Text #12

Max Range: 1.8042. Min Range: -1.8042

Max Act: 1.3086. Min Act: -0.0000

Data Index: 1451046 (Python Code)

Max Activating Token Index: 556

Text #13

Max Range: 1.8042. Min Range: -1.8042

Max Act: 1.3070. Min Act: -0.0000

Data Index: 1433372 (Python Code)

Max Activating Token Index: 741

Text #14

Max Range: 1.8042. Min Range: -1.8042

Max Act: 1.2710. Min Act: -0.0000

Data Index: 1641046 (Python Code)

Max Activating Token Index: 809

Text #15

Max Range: 1.8042. Min Range: -1.8042

Max Act: 1.3011. Min Act: -0.0000

Data Index: 1467252 (Python Code)

Max Activating Token Index: 108

Text #16

Max Range: 1.8042. Min Range: -1.8042

Max Act: 1.3293. Min Act: -0.0000

Data Index: 1483676 (Python Code)

Max Activating Token Index: 519

Text #17

Max Range: 1.8042. Min Range: -1.8042

Max Act: 1.2618. Min Act: -0.0000

Data Index: 1484934 (Python Code)

Max Activating Token Index: 850

Text #18

Max Range: 1.8042. Min Range: -1.8042

Max Act: 1.3324. Min Act: -0.0000

Data Index: 1497987 (Python Code)

Max Activating Token Index: 108

Text #19

Max Range: 1.8042. Min Range: -1.8042

Max Act: 1.3905. Min Act: -0.0000

Data Index: 1655626 (Python Code)

Max Activating Token Index: 580