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

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

Neuron 4240 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: 4.4598. Min Range: -4.4598

Max Act: 4.2945. Min Act: -0.0000

Data Index: 1460795 (Python Code)

Max Activating Token Index: 19

Text #1

Max Range: 4.4598. Min Range: -4.4598

Max Act: 4.4598. Min Act: -0.0000

Data Index: 1540016 (Python Code)

Max Activating Token Index: 33

Text #2

Max Range: 4.4598. Min Range: -4.4598

Max Act: 3.7218. Min Act: -0.0000

Data Index: 1504964 (Python Code)

Max Activating Token Index: 669

Text #3

Max Range: 4.4598. Min Range: -4.4598

Max Act: 3.4921. Min Act: -0.0000

Data Index: 1395380 (Python Code)

Max Activating Token Index: 42

Text #4

Max Range: 4.4598. Min Range: -4.4598

Max Act: 3.4421. Min Act: -0.0000

Data Index: 1412213 (Python Code)

Max Activating Token Index: 252

Text #5

Max Range: 4.4598. Min Range: -4.4598

Max Act: 3.4265. Min Act: -0.0000

Data Index: 1621731 (Python Code)

Max Activating Token Index: 357

Text #6

Max Range: 4.4598. Min Range: -4.4598

Max Act: 3.3772. Min Act: -0.0000

Data Index: 1640801 (Python Code)

Max Activating Token Index: 790

Text #7

Max Range: 4.4598. Min Range: -4.4598

Max Act: 3.3383. Min Act: -0.0000

Data Index: 1509874 (Python Code)

Max Activating Token Index: 14

Text #8

Max Range: 4.4598. Min Range: -4.4598

Max Act: 3.2689. Min Act: -0.0000

Data Index: 1632597 (Python Code)

Max Activating Token Index: 590

Text #9

Max Range: 4.4598. Min Range: -4.4598

Max Act: 3.1643. Min Act: -0.0000

Data Index: 1514305 (Python Code)

Max Activating Token Index: 51

Text #10

Max Range: 4.4598. Min Range: -4.4598

Max Act: 3.1554. Min Act: -0.0000

Data Index: 1584724 (Python Code)

Max Activating Token Index: 504

Text #11

Max Range: 4.4598. Min Range: -4.4598

Max Act: 3.0043. Min Act: -0.0000

Data Index: 1517042 (Python Code)

Max Activating Token Index: 789

Text #12

Max Range: 4.4598. Min Range: -4.4598

Max Act: 3.1544. Min Act: -0.0000

Data Index: 1461904 (Python Code)

Max Activating Token Index: 49

Text #13

Max Range: 4.4598. Min Range: -4.4598

Max Act: 3.2773. Min Act: -0.0000

Data Index: 1450905 (Python Code)

Max Activating Token Index: 985

Text #14

Max Range: 4.4598. Min Range: -4.4598

Max Act: 3.1212. Min Act: -0.0000

Data Index: 1603614 (Python Code)

Max Activating Token Index: 270

Text #15

Max Range: 4.4598. Min Range: -4.4598

Max Act: 3.1016. Min Act: -0.0000

Data Index: 1436536 (Python Code)

Max Activating Token Index: 63

Text #16

Max Range: 4.4598. Min Range: -4.4598

Max Act: 3.1014. Min Act: -0.0000

Data Index: 1493072 (Python Code)

Max Activating Token Index: 684

Text #17

Max Range: 4.4598. Min Range: -4.4598

Max Act: 3.0861. Min Act: -0.0000

Data Index: 1514876 (Python Code)

Max Activating Token Index: 781

Text #18

Max Range: 4.4598. Min Range: -4.4598

Max Act: 2.8085. Min Act: -0.0000

Data Index: 1472102 (Python Code)

Max Activating Token Index: 467

Text #19

Max Range: 4.4598. Min Range: -4.4598

Max Act: 3.0516. Min Act: -0.0000

Data Index: 1636819 (Python Code)

Max Activating Token Index: 236