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

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

Neuron 1858 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4269. Min Range: -1.4269

Max Act: 1.4125. Min Act: -0.0001

Data Index: 1532612 (Python Code)

Max Activating Token Index: 123

Text #1

Max Range: 1.4269. Min Range: -1.4269

Max Act: 1.3749. Min Act: -0.0000

Data Index: 1448262 (Python Code)

Max Activating Token Index: 255

Text #2

Max Range: 1.4269. Min Range: -1.4269

Max Act: 1.4087. Min Act: -0.0001

Data Index: 1366239 (Python Code)

Max Activating Token Index: 587

Text #3

Max Range: 1.4269. Min Range: -1.4269

Max Act: 1.3243. Min Act: -0.0001

Data Index: 1391516 (Python Code)

Max Activating Token Index: 8

Text #4

Max Range: 1.4269. Min Range: -1.4269

Max Act: 1.4269. Min Act: -0.0001

Data Index: 1486103 (Python Code)

Max Activating Token Index: 820

Text #5

Max Range: 1.4269. Min Range: -1.4269

Max Act: 1.3653. Min Act: -0.0001

Data Index: 1469528 (Python Code)

Max Activating Token Index: 167

Text #6

Max Range: 1.4269. Min Range: -1.4269

Max Act: 1.3279. Min Act: -0.0000

Data Index: 1514328 (Python Code)

Max Activating Token Index: 547

Text #7

Max Range: 1.4269. Min Range: -1.4269

Max Act: 1.3871. Min Act: -0.0001

Data Index: 1374377 (Python Code)

Max Activating Token Index: 603

Text #8

Max Range: 1.4269. Min Range: -1.4269

Max Act: 1.3555. Min Act: -0.0001

Data Index: 1562953 (Python Code)

Max Activating Token Index: 973

Text #9

Max Range: 1.4269. Min Range: -1.4269

Max Act: 1.3257. Min Act: -0.0000

Data Index: 1478355 (Python Code)

Max Activating Token Index: 461

Text #10

Max Range: 1.4269. Min Range: -1.4269

Max Act: 1.3195. Min Act: -0.0001

Data Index: 1446432 (Python Code)

Max Activating Token Index: 815

Text #11

Max Range: 1.4269. Min Range: -1.4269

Max Act: 1.2437. Min Act: -0.0001

Data Index: 1609608 (Python Code)

Max Activating Token Index: 117

Text #12

Max Range: 1.4269. Min Range: -1.4269

Max Act: 1.3357. Min Act: -0.0001

Data Index: 1469386 (Python Code)

Max Activating Token Index: 196

Text #13

Max Range: 1.4269. Min Range: -1.4269

Max Act: 1.4165. Min Act: -0.0000

Data Index: 1647066 (Python Code)

Max Activating Token Index: 104

Text #14

Max Range: 1.4269. Min Range: -1.4269

Max Act: 1.2146. Min Act: -0.0001

Data Index: 1636637 (Python Code)

Max Activating Token Index: 42

Text #15

Max Range: 1.4269. Min Range: -1.4269

Max Act: 1.2457. Min Act: -0.0001

Data Index: 1441446 (Python Code)

Max Activating Token Index: 423

Text #16

Max Range: 1.4269. Min Range: -1.4269

Max Act: 1.3140. Min Act: -0.0001

Data Index: 1399605 (Python Code)

Max Activating Token Index: 1001

Text #17

Max Range: 1.4269. Min Range: -1.4269

Max Act: 1.2211. Min Act: -0.0001

Data Index: 1388139 (Python Code)

Max Activating Token Index: 912

Text #18

Max Range: 1.4269. Min Range: -1.4269

Max Act: 1.1758. Min Act: -0.0000

Data Index: 1582383 (Python Code)

Max Activating Token Index: 594

Text #19

Max Range: 1.4269. Min Range: -1.4269

Max Act: 1.3274. Min Act: -0.0001

Data Index: 1517255 (Python Code)

Max Activating Token Index: 55