Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1836 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.7165. Min Range: -2.7165

Max Act: 2.5863. Min Act: -0.0000

Data Index: 1419934 (Python Code)

Max Activating Token Index: 58

Text #1

Max Range: 2.7165. Min Range: -2.7165

Max Act: 2.4359. Min Act: -0.0000

Data Index: 1498737 (Python Code)

Max Activating Token Index: 54

Text #2

Max Range: 2.7165. Min Range: -2.7165

Max Act: 2.7165. Min Act: -0.0000

Data Index: 1410882 (Python Code)

Max Activating Token Index: 68

Text #3

Max Range: 2.7165. Min Range: -2.7165

Max Act: 2.2845. Min Act: -0.0000

Data Index: 1371422 (Python Code)

Max Activating Token Index: 38

Text #4

Max Range: 2.7165. Min Range: -2.7165

Max Act: 2.2388. Min Act: -0.0000

Data Index: 1533170 (Python Code)

Max Activating Token Index: 42

Text #5

Max Range: 2.7165. Min Range: -2.7165

Max Act: 2.3404. Min Act: -0.0000

Data Index: 1645945 (Python Code)

Max Activating Token Index: 57

Text #6

Max Range: 2.7165. Min Range: -2.7165

Max Act: 2.3404. Min Act: -0.0000

Data Index: 1474050 (Python Code)

Max Activating Token Index: 57

Text #7

Max Range: 2.7165. Min Range: -2.7165

Max Act: 2.4276. Min Act: -0.0000

Data Index: 1610849 (Python Code)

Max Activating Token Index: 54

Text #8

Max Range: 2.7165. Min Range: -2.7165

Max Act: 2.2836. Min Act: -0.0000

Data Index: 1410480 (Python Code)

Max Activating Token Index: 35

Text #9

Max Range: 2.7165. Min Range: -2.7165

Max Act: 2.1321. Min Act: -0.0000

Data Index: 1572475 (Python Code)

Max Activating Token Index: 58

Text #10

Max Range: 2.7165. Min Range: -2.7165

Max Act: 2.2537. Min Act: -0.0000

Data Index: 1611545 (Python Code)

Max Activating Token Index: 37

Text #11

Max Range: 2.7165. Min Range: -2.7165

Max Act: 2.2357. Min Act: -0.0000

Data Index: 1455206 (Python Code)

Max Activating Token Index: 41

Text #12

Max Range: 2.7165. Min Range: -2.7165

Max Act: 2.2357. Min Act: -0.0000

Data Index: 1418491 (Python Code)

Max Activating Token Index: 41

Text #13

Max Range: 2.7165. Min Range: -2.7165

Max Act: 1.9921. Min Act: -0.0000

Data Index: 1569257 (Python Code)

Max Activating Token Index: 51

Text #14

Max Range: 2.7165. Min Range: -2.7165

Max Act: 2.2244. Min Act: -0.0000

Data Index: 1620721 (Python Code)

Max Activating Token Index: 58

Text #15

Max Range: 2.7165. Min Range: -2.7165

Max Act: 2.1024. Min Act: -0.0000

Data Index: 1482236 (Python Code)

Max Activating Token Index: 40

Text #16

Max Range: 2.7165. Min Range: -2.7165

Max Act: 2.1926. Min Act: -0.0000

Data Index: 1532907 (Python Code)

Max Activating Token Index: 766

Text #17

Max Range: 2.7165. Min Range: -2.7165

Max Act: 2.1942. Min Act: -0.0000

Data Index: 1441322 (Python Code)

Max Activating Token Index: 37

Text #18

Max Range: 2.7165. Min Range: -2.7165

Max Act: 2.1942. Min Act: -0.0000

Data Index: 1606572 (Python Code)

Max Activating Token Index: 37

Text #19

Max Range: 2.7165. Min Range: -2.7165

Max Act: 2.1942. Min Act: -0.0000

Data Index: 1465585 (Python Code)

Max Activating Token Index: 37