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

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

Neuron 104 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2448. Min Range: -0.2448

Max Act: 0.2448. Min Act: -0.0002

Data Index: 1595014 (Python Code)

Max Activating Token Index: 19

Text #1

Max Range: 0.2448. Min Range: -0.2448

Max Act: 0.2414. Min Act: -0.0002

Data Index: 1604534 (Python Code)

Max Activating Token Index: 24

Text #2

Max Range: 0.2448. Min Range: -0.2448

Max Act: 0.2295. Min Act: -0.0002

Data Index: 1371404 (Python Code)

Max Activating Token Index: 76

Text #3

Max Range: 0.2448. Min Range: -0.2448

Max Act: 0.2193. Min Act: -0.0002

Data Index: 1447826 (Python Code)

Max Activating Token Index: 56

Text #4

Max Range: 0.2448. Min Range: -0.2448

Max Act: 0.2120. Min Act: -0.0002

Data Index: 1453179 (Python Code)

Max Activating Token Index: 31

Text #5

Max Range: 0.2448. Min Range: -0.2448

Max Act: 0.2251. Min Act: -0.0002

Data Index: 1511256 (Python Code)

Max Activating Token Index: 80

Text #6

Max Range: 0.2448. Min Range: -0.2448

Max Act: 0.2152. Min Act: -0.0002

Data Index: 1607851 (Python Code)

Max Activating Token Index: 22

Text #7

Max Range: 0.2448. Min Range: -0.2448

Max Act: 0.2077. Min Act: -0.0002

Data Index: 1570645 (Python Code)

Max Activating Token Index: 11

Text #8

Max Range: 0.2448. Min Range: -0.2448

Max Act: 0.2152. Min Act: -0.0002

Data Index: 1623495 (Python Code)

Max Activating Token Index: 50

Text #9

Max Range: 0.2448. Min Range: -0.2448

Max Act: 0.2142. Min Act: -0.0002

Data Index: 1462667 (Python Code)

Max Activating Token Index: 44

Text #10

Max Range: 0.2448. Min Range: -0.2448

Max Act: 0.2069. Min Act: -0.0002

Data Index: 1400242 (Python Code)

Max Activating Token Index: 17

Text #11

Max Range: 0.2448. Min Range: -0.2448

Max Act: 0.2130. Min Act: -0.0002

Data Index: 1592672 (Python Code)

Max Activating Token Index: 48

Text #12

Max Range: 0.2448. Min Range: -0.2448

Max Act: 0.2124. Min Act: -0.0002

Data Index: 1446203 (Python Code)

Max Activating Token Index: 19

Text #13

Max Range: 0.2448. Min Range: -0.2448

Max Act: 0.2041. Min Act: -0.0002

Data Index: 1622520 (Python Code)

Max Activating Token Index: 82

Text #14

Max Range: 0.2448. Min Range: -0.2448

Max Act: 0.2111. Min Act: -0.0002

Data Index: 1530254 (Python Code)

Max Activating Token Index: 15

Text #15

Max Range: 0.2448. Min Range: -0.2448

Max Act: 0.2059. Min Act: -0.0002

Data Index: 1518542 (Python Code)

Max Activating Token Index: 14

Text #16

Max Range: 0.2448. Min Range: -0.2448

Max Act: 0.1983. Min Act: -0.0002

Data Index: 1506936 (Python Code)

Max Activating Token Index: 30

Text #17

Max Range: 0.2448. Min Range: -0.2448

Max Act: 0.2049. Min Act: -0.0002

Data Index: 1380111 (Python Code)

Max Activating Token Index: 13

Text #18

Max Range: 0.2448. Min Range: -0.2448

Max Act: 0.2045. Min Act: -0.0002

Data Index: 1490255 (Python Code)

Max Activating Token Index: 103

Text #19

Max Range: 0.2448. Min Range: -0.2448

Max Act: 0.2022. Min Act: -0.0002

Data Index: 1550002 (Python Code)

Max Activating Token Index: 88