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

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

Neuron 3352 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7398. Min Range: -0.7398

Max Act: 0.7351. Min Act: -0.0000

Data Index: 1404404 (Python Code)

Max Activating Token Index: 960

Text #1

Max Range: 0.7398. Min Range: -0.7398

Max Act: 0.7398. Min Act: -0.0000

Data Index: 1425988 (Python Code)

Max Activating Token Index: 777

Text #2

Max Range: 0.7398. Min Range: -0.7398

Max Act: 0.7141. Min Act: -0.0000

Data Index: 1550737 (Python Code)

Max Activating Token Index: 109

Text #3

Max Range: 0.7398. Min Range: -0.7398

Max Act: 0.6557. Min Act: -0.0000

Data Index: 1456856 (Python Code)

Max Activating Token Index: 451

Text #4

Max Range: 0.7398. Min Range: -0.7398

Max Act: 0.6333. Min Act: -0.0000

Data Index: 1654747 (Python Code)

Max Activating Token Index: 125

Text #5

Max Range: 0.7398. Min Range: -0.7398

Max Act: 0.6265. Min Act: -0.0000

Data Index: 1526072 (Python Code)

Max Activating Token Index: 584

Text #6

Max Range: 0.7398. Min Range: -0.7398

Max Act: 0.5999. Min Act: -0.0000

Data Index: 1624933 (Python Code)

Max Activating Token Index: 640

Text #7

Max Range: 0.7398. Min Range: -0.7398

Max Act: 0.5913. Min Act: -0.0000

Data Index: 1374831 (Python Code)

Max Activating Token Index: 805

Text #8

Max Range: 0.7398. Min Range: -0.7398

Max Act: 0.5726. Min Act: -0.0000

Data Index: 1577179 (Python Code)

Max Activating Token Index: 256

Text #9

Max Range: 0.7398. Min Range: -0.7398

Max Act: 0.5294. Min Act: -0.0000

Data Index: 1522384 (Python Code)

Max Activating Token Index: 271

Text #10

Max Range: 0.7398. Min Range: -0.7398

Max Act: 0.5468. Min Act: -0.0000

Data Index: 1422671 (Python Code)

Max Activating Token Index: 192

Text #11

Max Range: 0.7398. Min Range: -0.7398

Max Act: 0.5041. Min Act: -0.0000

Data Index: 1595291 (Python Code)

Max Activating Token Index: 686

Text #12

Max Range: 0.7398. Min Range: -0.7398

Max Act: 0.4866. Min Act: -0.0000

Data Index: 1622871 (Python Code)

Max Activating Token Index: 795

Text #13

Max Range: 0.7398. Min Range: -0.7398

Max Act: 0.5089. Min Act: -0.0000

Data Index: 1625793 (Python Code)

Max Activating Token Index: 605

Text #14

Max Range: 0.7398. Min Range: -0.7398

Max Act: 0.4394. Min Act: -0.0000

Data Index: 1431353 (Python Code)

Max Activating Token Index: 934

Text #15

Max Range: 0.7398. Min Range: -0.7398

Max Act: 0.5033. Min Act: -0.0000

Data Index: 1506457 (Python Code)

Max Activating Token Index: 402

Text #16

Max Range: 0.7398. Min Range: -0.7398

Max Act: 0.4895. Min Act: -0.0000

Data Index: 1636022 (Python Code)

Max Activating Token Index: 372

Text #17

Max Range: 0.7398. Min Range: -0.7398

Max Act: 0.4620. Min Act: -0.0000

Data Index: 1485226 (Python Code)

Max Activating Token Index: 937

Text #18

Max Range: 0.7398. Min Range: -0.7398

Max Act: 0.4607. Min Act: -0.0000

Data Index: 1412343 (Python Code)

Max Activating Token Index: 634

Text #19

Max Range: 0.7398. Min Range: -0.7398

Max Act: 0.4706. Min Act: -0.0000

Data Index: 1458435 (Python Code)

Max Activating Token Index: 90