Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 22 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0297. Min Act: -0.0005

Data Index: 1633139 (Python Code)

Max Activating Token Index: 65

Text #1

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0284. Min Act: -0.0005

Data Index: 1572558 (Python Code)

Max Activating Token Index: 65

Text #2

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0284. Min Act: -0.0005

Data Index: 1563909 (Python Code)

Max Activating Token Index: 42

Text #3

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0280. Min Act: -0.0005

Data Index: 1650394 (Python Code)

Max Activating Token Index: 42

Text #4

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0272. Min Act: -0.0005

Data Index: 1477262 (Python Code)

Max Activating Token Index: 66

Text #5

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0278. Min Act: -0.0005

Data Index: 1648936 (Python Code)

Max Activating Token Index: 43

Text #6

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0271. Min Act: -0.0005

Data Index: 1426547 (Python Code)

Max Activating Token Index: 43

Text #7

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0272. Min Act: -0.0005

Data Index: 1488450 (Python Code)

Max Activating Token Index: 41

Text #8

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0277. Min Act: -0.0005

Data Index: 1603672 (Python Code)

Max Activating Token Index: 43

Text #9

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0276. Min Act: -0.0005

Data Index: 1457437 (Python Code)

Max Activating Token Index: 39

Text #10

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0269. Min Act: -0.0005

Data Index: 1629428 (Python Code)

Max Activating Token Index: 70

Text #11

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0274. Min Act: -0.0005

Data Index: 1615315 (Python Code)

Max Activating Token Index: 39

Text #12

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0274. Min Act: -0.0005

Data Index: 1547453 (Python Code)

Max Activating Token Index: 65

Text #13

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0285. Min Act: -0.0005

Data Index: 1586927 (Python Code)

Max Activating Token Index: 59

Text #14

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0267. Min Act: -0.0005

Data Index: 1493532 (Python Code)

Max Activating Token Index: 40

Text #15

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0267. Min Act: -0.0005

Data Index: 1407688 (Python Code)

Max Activating Token Index: 65

Text #16

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0272. Min Act: -0.0005

Data Index: 1433482 (Python Code)

Max Activating Token Index: 62

Text #17

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0273. Min Act: -0.0005

Data Index: 1593267 (Python Code)

Max Activating Token Index: 42

Text #18

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0266. Min Act: -0.0005

Data Index: 1484247 (Python Code)

Max Activating Token Index: 43

Text #19

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0277. Min Act: -0.0005

Data Index: 1626731 (Python Code)

Max Activating Token Index: 42