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

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

Neuron 5816 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: 0.1364. Min Range: -0.1364

Max Act: 0.1364. Min Act: -0.0000

Data Index: 1636733 (Python Code)

Max Activating Token Index: 371

Text #1

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.1182. Min Act: -0.0000

Data Index: 1457789 (Python Code)

Max Activating Token Index: 334

Text #2

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.1306. Min Act: -0.0000

Data Index: 1486169 (Python Code)

Max Activating Token Index: 447

Text #3

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.1306. Min Act: -0.0000

Data Index: 1453536 (Python Code)

Max Activating Token Index: 56

Text #4

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.1200. Min Act: -0.0001

Data Index: 1500883 (Python Code)

Max Activating Token Index: 319

Text #5

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.1186. Min Act: -0.0001

Data Index: 751391 (C4 (Web Text))

Max Activating Token Index: 5

Text #6

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.1058. Min Act: -0.0000

Data Index: 1411338 (Python Code)

Max Activating Token Index: 111

Text #7

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.1132. Min Act: -0.0000

Data Index: 1608544 (Python Code)

Max Activating Token Index: 228

Text #8

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.1007. Min Act: -0.0000

Data Index: 1481734 (Python Code)

Max Activating Token Index: 583

Text #9

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.1099. Min Act: -0.0000

Data Index: 1505784 (Python Code)

Max Activating Token Index: 101

Text #10

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.1061. Min Act: -0.0000

Data Index: 1465512 (Python Code)

Max Activating Token Index: 789

Text #11

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.1037. Min Act: -0.0001

Data Index: 1022246 (C4 (Web Text))

Max Activating Token Index: 332

Text #12

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.1036. Min Act: -0.0000

Data Index: 1362012 (Python Code)

Max Activating Token Index: 177

Text #13

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.1143. Min Act: -0.0000

Data Index: 711073 (C4 (Web Text))

Max Activating Token Index: 630

Text #14

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.0971. Min Act: -0.0000

Data Index: 1398560 (Python Code)

Max Activating Token Index: 360

Text #15

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.0970. Min Act: -0.0000

Data Index: 1497788 (Python Code)

Max Activating Token Index: 394

Text #16

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.1014. Min Act: -0.0000

Data Index: 1371840 (Python Code)

Max Activating Token Index: 858

Text #17

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.0910. Min Act: -0.0001

Data Index: 84829 (C4 (Web Text))

Max Activating Token Index: 682

Text #18

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.1126. Min Act: -0.0001

Data Index: 166590 (C4 (Web Text))

Max Activating Token Index: 749

Text #19

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.1045. Min Act: -0.0000

Data Index: 1606137 (Python Code)

Max Activating Token Index: 811