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

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

Neuron 3326 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: 0.8825. Min Range: -0.8825

Max Act: 0.8825. Min Act: -0.0000

Data Index: 1464859 (Python Code)

Max Activating Token Index: 14

Text #1

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.8292. Min Act: -0.0000

Data Index: 1547432 (Python Code)

Max Activating Token Index: 76

Text #2

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.7791. Min Act: -0.0000

Data Index: 1399297 (Python Code)

Max Activating Token Index: 27

Text #3

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.7086. Min Act: -0.0000

Data Index: 1478262 (Python Code)

Max Activating Token Index: 394

Text #4

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.7275. Min Act: -0.0000

Data Index: 1560614 (Python Code)

Max Activating Token Index: 683

Text #5

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.7144. Min Act: -0.0000

Data Index: 1461459 (Python Code)

Max Activating Token Index: 382

Text #6

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.7170. Min Act: -0.0000

Data Index: 1420261 (Python Code)

Max Activating Token Index: 36

Text #7

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.6325. Min Act: -0.0000

Data Index: 1367273 (Python Code)

Max Activating Token Index: 602

Text #8

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.6317. Min Act: -0.0000

Data Index: 1394007 (Python Code)

Max Activating Token Index: 936

Text #9

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.6933. Min Act: -0.0000

Data Index: 1440126 (Python Code)

Max Activating Token Index: 278

Text #10

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.7189. Min Act: -0.0000

Data Index: 1523928 (Python Code)

Max Activating Token Index: 508

Text #11

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.6611. Min Act: -0.0000

Data Index: 1531280 (Python Code)

Max Activating Token Index: 245

Text #12

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.7322. Min Act: -0.0000

Data Index: 1420279 (Python Code)

Max Activating Token Index: 887

Text #13

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.7309. Min Act: -0.0000

Data Index: 1566333 (Python Code)

Max Activating Token Index: 726

Text #14

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.5915. Min Act: -0.0000

Data Index: 1437164 (Python Code)

Max Activating Token Index: 185

Text #15

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.6550. Min Act: -0.0000

Data Index: 1592857 (Python Code)

Max Activating Token Index: 385

Text #16

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.6934. Min Act: -0.0000

Data Index: 1648943 (Python Code)

Max Activating Token Index: 790

Text #17

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.6163. Min Act: -0.0000

Data Index: 1441667 (Python Code)

Max Activating Token Index: 857

Text #18

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.6631. Min Act: -0.0000

Data Index: 1601179 (Python Code)

Max Activating Token Index: 67

Text #19

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.7321. Min Act: -0.0000

Data Index: 1629157 (Python Code)

Max Activating Token Index: 834