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

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

Neuron 1617 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: 0.2428. Min Range: -0.2428

Max Act: 0.2428. Min Act: -0.0000

Data Index: 551424 (C4 (Web Text))

Max Activating Token Index: 1009

Text #1

Max Range: 0.2428. Min Range: -0.2428

Max Act: 0.2109. Min Act: -0.0000

Data Index: 439949 (C4 (Web Text))

Max Activating Token Index: 865

Text #2

Max Range: 0.2428. Min Range: -0.2428

Max Act: 0.2159. Min Act: -0.0000

Data Index: 839196 (C4 (Web Text))

Max Activating Token Index: 1013

Text #3

Max Range: 0.2428. Min Range: -0.2428

Max Act: 0.2252. Min Act: -0.0000

Data Index: 526775 (C4 (Web Text))

Max Activating Token Index: 12

Text #4

Max Range: 0.2428. Min Range: -0.2428

Max Act: 0.2255. Min Act: -0.0000

Data Index: 1655772 (Python Code)

Max Activating Token Index: 818

Text #5

Max Range: 0.2428. Min Range: -0.2428

Max Act: 0.2344. Min Act: -0.0000

Data Index: 220108 (C4 (Web Text))

Max Activating Token Index: 67

Text #6

Max Range: 0.2428. Min Range: -0.2428

Max Act: 0.1977. Min Act: -0.0000

Data Index: 1213995 (C4 (Web Text))

Max Activating Token Index: 740

Text #7

Max Range: 0.2428. Min Range: -0.2428

Max Act: 0.2096. Min Act: -0.0000

Data Index: 191035 (C4 (Web Text))

Max Activating Token Index: 515

Text #8

Max Range: 0.2428. Min Range: -0.2428

Max Act: 0.2044. Min Act: -0.0000

Data Index: 175808 (C4 (Web Text))

Max Activating Token Index: 420

Text #9

Max Range: 0.2428. Min Range: -0.2428

Max Act: 0.2005. Min Act: -0.0000

Data Index: 434779 (C4 (Web Text))

Max Activating Token Index: 78

Text #10

Max Range: 0.2428. Min Range: -0.2428

Max Act: 0.2161. Min Act: -0.0000

Data Index: 302817 (C4 (Web Text))

Max Activating Token Index: 942

Text #11

Max Range: 0.2428. Min Range: -0.2428

Max Act: 0.2048. Min Act: -0.0000

Data Index: 1603890 (Python Code)

Max Activating Token Index: 55

Text #12

Max Range: 0.2428. Min Range: -0.2428

Max Act: 0.1903. Min Act: -0.0000

Data Index: 1260739 (C4 (Web Text))

Max Activating Token Index: 804

Text #13

Max Range: 0.2428. Min Range: -0.2428

Max Act: 0.1890. Min Act: -0.0000

Data Index: 647560 (C4 (Web Text))

Max Activating Token Index: 179

Text #14

Max Range: 0.2428. Min Range: -0.2428

Max Act: 0.1936. Min Act: -0.0000

Data Index: 1399376 (Python Code)

Max Activating Token Index: 648

Text #15

Max Range: 0.2428. Min Range: -0.2428

Max Act: 0.1693. Min Act: -0.0000

Data Index: 856812 (C4 (Web Text))

Max Activating Token Index: 387

Text #16

Max Range: 0.2428. Min Range: -0.2428

Max Act: 0.1985. Min Act: -0.0000

Data Index: 1634225 (Python Code)

Max Activating Token Index: 593

Text #17

Max Range: 0.2428. Min Range: -0.2428

Max Act: 0.1785. Min Act: -0.0000

Data Index: 144533 (C4 (Web Text))

Max Activating Token Index: 425

Text #18

Max Range: 0.2428. Min Range: -0.2428

Max Act: 0.1889. Min Act: -0.0000

Data Index: 885921 (C4 (Web Text))

Max Activating Token Index: 487

Text #19

Max Range: 0.2428. Min Range: -0.2428

Max Act: 0.1818. Min Act: -0.0000

Data Index: 231287 (C4 (Web Text))

Max Activating Token Index: 934