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

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

Neuron 1198 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: 1.1928. Min Range: -1.1928

Max Act: 1.1928. Min Act: -0.0000

Data Index: 1627196 (Python Code)

Max Activating Token Index: 49

Text #1

Max Range: 1.1928. Min Range: -1.1928

Max Act: 1.0839. Min Act: -0.0000

Data Index: 1549887 (Python Code)

Max Activating Token Index: 300

Text #2

Max Range: 1.1928. Min Range: -1.1928

Max Act: 1.0810. Min Act: -0.0000

Data Index: 1638031 (Python Code)

Max Activating Token Index: 177

Text #3

Max Range: 1.1928. Min Range: -1.1928

Max Act: 0.7999. Min Act: -0.0000

Data Index: 1448873 (Python Code)

Max Activating Token Index: 637

Text #4

Max Range: 1.1928. Min Range: -1.1928

Max Act: 0.8238. Min Act: -0.0000

Data Index: 1516756 (Python Code)

Max Activating Token Index: 587

Text #5

Max Range: 1.1928. Min Range: -1.1928

Max Act: 0.8792. Min Act: -0.0000

Data Index: 1630737 (Python Code)

Max Activating Token Index: 58

Text #6

Max Range: 1.1928. Min Range: -1.1928

Max Act: 0.8522. Min Act: -0.0000

Data Index: 1501108 (Python Code)

Max Activating Token Index: 187

Text #7

Max Range: 1.1928. Min Range: -1.1928

Max Act: 0.8079. Min Act: -0.0000

Data Index: 1600805 (Python Code)

Max Activating Token Index: 177

Text #8

Max Range: 1.1928. Min Range: -1.1928

Max Act: 0.8699. Min Act: -0.0000

Data Index: 1450481 (Python Code)

Max Activating Token Index: 61

Text #9

Max Range: 1.1928. Min Range: -1.1928

Max Act: 0.8020. Min Act: -0.0000

Data Index: 1395631 (Python Code)

Max Activating Token Index: 220

Text #10

Max Range: 1.1928. Min Range: -1.1928

Max Act: 0.7383. Min Act: -0.0000

Data Index: 1509710 (Python Code)

Max Activating Token Index: 297

Text #11

Max Range: 1.1928. Min Range: -1.1928

Max Act: 0.7825. Min Act: -0.0000

Data Index: 1577973 (Python Code)

Max Activating Token Index: 72

Text #12

Max Range: 1.1928. Min Range: -1.1928

Max Act: 0.8477. Min Act: -0.0000

Data Index: 1646681 (Python Code)

Max Activating Token Index: 789

Text #13

Max Range: 1.1928. Min Range: -1.1928

Max Act: 0.8218. Min Act: -0.0000

Data Index: 1518458 (Python Code)

Max Activating Token Index: 886

Text #14

Max Range: 1.1928. Min Range: -1.1928

Max Act: 0.7380. Min Act: -0.0000

Data Index: 1584593 (Python Code)

Max Activating Token Index: 82

Text #15

Max Range: 1.1928. Min Range: -1.1928

Max Act: 0.7036. Min Act: -0.0000

Data Index: 1480419 (Python Code)

Max Activating Token Index: 913

Text #16

Max Range: 1.1928. Min Range: -1.1928

Max Act: 0.7741. Min Act: -0.0000

Data Index: 1402730 (Python Code)

Max Activating Token Index: 961

Text #17

Max Range: 1.1928. Min Range: -1.1928

Max Act: 0.7502. Min Act: -0.0000

Data Index: 1507525 (Python Code)

Max Activating Token Index: 257

Text #18

Max Range: 1.1928. Min Range: -1.1928

Max Act: 0.7177. Min Act: -0.0000

Data Index: 1493634 (Python Code)

Max Activating Token Index: 83

Text #19

Max Range: 1.1928. Min Range: -1.1928

Max Act: 0.7377. Min Act: -0.0000

Data Index: 1589647 (Python Code)

Max Activating Token Index: 478