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

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

Neuron 1664 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.7969. Min Range: -4.7969

Max Act: 4.7969. Min Act: -0.0001

Data Index: 1510024 (Python Code)

Max Activating Token Index: 28

Text #1

Max Range: 4.7969. Min Range: -4.7969

Max Act: 4.6521. Min Act: -0.0001

Data Index: 1627005 (Python Code)

Max Activating Token Index: 40

Text #2

Max Range: 4.7969. Min Range: -4.7969

Max Act: 4.7325. Min Act: -0.0001

Data Index: 1610380 (Python Code)

Max Activating Token Index: 20

Text #3

Max Range: 4.7969. Min Range: -4.7969

Max Act: 4.7220. Min Act: -0.0000

Data Index: 1568277 (Python Code)

Max Activating Token Index: 24

Text #4

Max Range: 4.7969. Min Range: -4.7969

Max Act: 4.7179. Min Act: -0.0000

Data Index: 1631511 (Python Code)

Max Activating Token Index: 22

Text #5

Max Range: 4.7969. Min Range: -4.7969

Max Act: 4.3811. Min Act: -0.0001

Data Index: 1599468 (Python Code)

Max Activating Token Index: 42

Text #6

Max Range: 4.7969. Min Range: -4.7969

Max Act: 4.3783. Min Act: -0.0001

Data Index: 1377668 (Python Code)

Max Activating Token Index: 27

Text #7

Max Range: 4.7969. Min Range: -4.7969

Max Act: 4.3032. Min Act: -0.0001

Data Index: 1472699 (Python Code)

Max Activating Token Index: 15

Text #8

Max Range: 4.7969. Min Range: -4.7969

Max Act: 4.1343. Min Act: -0.0001

Data Index: 1419632 (Python Code)

Max Activating Token Index: 57

Text #9

Max Range: 4.7969. Min Range: -4.7969

Max Act: 4.2298. Min Act: -0.0001

Data Index: 1619844 (Python Code)

Max Activating Token Index: 39

Text #10

Max Range: 4.7969. Min Range: -4.7969

Max Act: 4.0463. Min Act: -0.0000

Data Index: 1536304 (Python Code)

Max Activating Token Index: 18

Text #11

Max Range: 4.7969. Min Range: -4.7969

Max Act: 3.9995. Min Act: -0.0001

Data Index: 1635287 (Python Code)

Max Activating Token Index: 826

Text #12

Max Range: 4.7969. Min Range: -4.7969

Max Act: 3.9737. Min Act: -0.0000

Data Index: 1372905 (Python Code)

Max Activating Token Index: 53

Text #13

Max Range: 4.7969. Min Range: -4.7969

Max Act: 4.0756. Min Act: -0.0000

Data Index: 1609767 (Python Code)

Max Activating Token Index: 63

Text #14

Max Range: 4.7969. Min Range: -4.7969

Max Act: 3.7307. Min Act: -0.0000

Data Index: 1471412 (Python Code)

Max Activating Token Index: 983

Text #15

Max Range: 4.7969. Min Range: -4.7969

Max Act: 4.0107. Min Act: -0.0000

Data Index: 1572900 (Python Code)

Max Activating Token Index: 833

Text #16

Max Range: 4.7969. Min Range: -4.7969

Max Act: 3.8513. Min Act: -0.0001

Data Index: 1384552 (Python Code)

Max Activating Token Index: 909

Text #17

Max Range: 4.7969. Min Range: -4.7969

Max Act: 3.8223. Min Act: -0.0001

Data Index: 1544022 (Python Code)

Max Activating Token Index: 1011

Text #18

Max Range: 4.7969. Min Range: -4.7969

Max Act: 3.8366. Min Act: -0.0001

Data Index: 1465432 (Python Code)

Max Activating Token Index: 963

Text #19

Max Range: 4.7969. Min Range: -4.7969

Max Act: 3.7781. Min Act: -0.0000

Data Index: 1617777 (Python Code)

Max Activating Token Index: 996