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

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

Neuron 2457 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: 1.1854. Min Range: -1.1854

Max Act: 1.1248. Min Act: -0.0000

Data Index: 1440437 (Python Code)

Max Activating Token Index: 1009

Text #1

Max Range: 1.1854. Min Range: -1.1854

Max Act: 1.0756. Min Act: -0.0000

Data Index: 1483638 (Python Code)

Max Activating Token Index: 974

Text #2

Max Range: 1.1854. Min Range: -1.1854

Max Act: 0.9176. Min Act: -0.0000

Data Index: 1615002 (Python Code)

Max Activating Token Index: 923

Text #3

Max Range: 1.1854. Min Range: -1.1854

Max Act: 1.1854. Min Act: -0.0000

Data Index: 1656122 (Python Code)

Max Activating Token Index: 988

Text #4

Max Range: 1.1854. Min Range: -1.1854

Max Act: 1.1274. Min Act: -0.0000

Data Index: 1361424 (Python Code)

Max Activating Token Index: 961

Text #5

Max Range: 1.1854. Min Range: -1.1854

Max Act: 1.0738. Min Act: -0.0000

Data Index: 1638711 (Python Code)

Max Activating Token Index: 985

Text #6

Max Range: 1.1854. Min Range: -1.1854

Max Act: 1.1660. Min Act: -0.0000

Data Index: 1386453 (Python Code)

Max Activating Token Index: 998

Text #7

Max Range: 1.1854. Min Range: -1.1854

Max Act: 1.0224. Min Act: -0.0000

Data Index: 1554544 (Python Code)

Max Activating Token Index: 768

Text #8

Max Range: 1.1854. Min Range: -1.1854

Max Act: 1.0883. Min Act: -0.0000

Data Index: 1512215 (Python Code)

Max Activating Token Index: 36

Text #9

Max Range: 1.1854. Min Range: -1.1854

Max Act: 1.0446. Min Act: -0.0000

Data Index: 1531399 (Python Code)

Max Activating Token Index: 589

Text #10

Max Range: 1.1854. Min Range: -1.1854

Max Act: 0.9713. Min Act: -0.0000

Data Index: 1555072 (Python Code)

Max Activating Token Index: 104

Text #11

Max Range: 1.1854. Min Range: -1.1854

Max Act: 0.9631. Min Act: -0.0000

Data Index: 1437243 (Python Code)

Max Activating Token Index: 786

Text #12

Max Range: 1.1854. Min Range: -1.1854

Max Act: 1.0275. Min Act: -0.0000

Data Index: 1653391 (Python Code)

Max Activating Token Index: 989

Text #13

Max Range: 1.1854. Min Range: -1.1854

Max Act: 1.0204. Min Act: -0.0000

Data Index: 1441879 (Python Code)

Max Activating Token Index: 870

Text #14

Max Range: 1.1854. Min Range: -1.1854

Max Act: 0.9829. Min Act: -0.0000

Data Index: 1423326 (Python Code)

Max Activating Token Index: 892

Text #15

Max Range: 1.1854. Min Range: -1.1854

Max Act: 1.0052. Min Act: -0.0000

Data Index: 1364067 (Python Code)

Max Activating Token Index: 944

Text #16

Max Range: 1.1854. Min Range: -1.1854

Max Act: 1.0117. Min Act: -0.0000

Data Index: 1603072 (Python Code)

Max Activating Token Index: 337

Text #17

Max Range: 1.1854. Min Range: -1.1854

Max Act: 1.0142. Min Act: -0.0000

Data Index: 1386055 (Python Code)

Max Activating Token Index: 885

Text #18

Max Range: 1.1854. Min Range: -1.1854

Max Act: 1.0008. Min Act: -0.0000

Data Index: 1600559 (Python Code)

Max Activating Token Index: 1009

Text #19

Max Range: 1.1854. Min Range: -1.1854

Max Act: 0.9928. Min Act: -0.0000

Data Index: 1522422 (Python Code)

Max Activating Token Index: 979