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

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

Neuron 5212 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1668. Min Act: -0.0000

Data Index: 1609588 (Python Code)

Max Activating Token Index: 6

Text #1

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1521. Min Act: -0.0000

Data Index: 1409089 (Python Code)

Max Activating Token Index: 6

Text #2

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1491. Min Act: -0.0000

Data Index: 1641331 (Python Code)

Max Activating Token Index: 16

Text #3

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1463. Min Act: -0.0000

Data Index: 1553194 (Python Code)

Max Activating Token Index: 7

Text #4

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1451. Min Act: -0.0000

Data Index: 1608176 (Python Code)

Max Activating Token Index: 17

Text #5

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1340. Min Act: -0.0000

Data Index: 1656658 (Python Code)

Max Activating Token Index: 13

Text #6

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1359. Min Act: -0.0000

Data Index: 957105 (C4 (Web Text))

Max Activating Token Index: 955

Text #7

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1239. Min Act: -0.0000

Data Index: 1454898 (Python Code)

Max Activating Token Index: 25

Text #8

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1214. Min Act: -0.0000

Data Index: 1561198 (Python Code)

Max Activating Token Index: 28

Text #9

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1194. Min Act: -0.0000

Data Index: 1382340 (Python Code)

Max Activating Token Index: 4

Text #10

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1275. Min Act: -0.0000

Data Index: 770727 (C4 (Web Text))

Max Activating Token Index: 209

Text #11

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1222. Min Act: -0.0000

Data Index: 1596924 (Python Code)

Max Activating Token Index: 4

Text #12

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1167. Min Act: -0.0000

Data Index: 1640302 (Python Code)

Max Activating Token Index: 23

Text #13

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1198. Min Act: -0.0000

Data Index: 1580114 (Python Code)

Max Activating Token Index: 5

Text #14

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1198. Min Act: -0.0000

Data Index: 1529981 (Python Code)

Max Activating Token Index: 5

Text #15

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1212. Min Act: -0.0000

Data Index: 1459543 (Python Code)

Max Activating Token Index: 25

Text #16

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1156. Min Act: -0.0000

Data Index: 1538761 (Python Code)

Max Activating Token Index: 21

Text #17

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1147. Min Act: -0.0000

Data Index: 1631070 (Python Code)

Max Activating Token Index: 7

Text #18

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1099. Min Act: -0.0000

Data Index: 1439918 (Python Code)

Max Activating Token Index: 27

Text #19

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1146. Min Act: -0.0000

Data Index: 1624917 (Python Code)

Max Activating Token Index: 5