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

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

Neuron 3787 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: 3.8275. Min Range: -3.8275

Max Act: 3.8275. Min Act: -0.0001

Data Index: 1364683 (Python Code)

Max Activating Token Index: 890

Text #1

Max Range: 3.8275. Min Range: -3.8275

Max Act: 3.4775. Min Act: -0.0001

Data Index: 1381443 (Python Code)

Max Activating Token Index: 459

Text #2

Max Range: 3.8275. Min Range: -3.8275

Max Act: 3.6345. Min Act: -0.0001

Data Index: 1589618 (Python Code)

Max Activating Token Index: 295

Text #3

Max Range: 3.8275. Min Range: -3.8275

Max Act: 3.3210. Min Act: -0.0001

Data Index: 1596552 (Python Code)

Max Activating Token Index: 736

Text #4

Max Range: 3.8275. Min Range: -3.8275

Max Act: 3.2735. Min Act: -0.0001

Data Index: 1482686 (Python Code)

Max Activating Token Index: 455

Text #5

Max Range: 3.8275. Min Range: -3.8275

Max Act: 3.3657. Min Act: -0.0001

Data Index: 1501371 (Python Code)

Max Activating Token Index: 248

Text #6

Max Range: 3.8275. Min Range: -3.8275

Max Act: 3.0909. Min Act: -0.0001

Data Index: 1587146 (Python Code)

Max Activating Token Index: 380

Text #7

Max Range: 3.8275. Min Range: -3.8275

Max Act: 3.1586. Min Act: -0.0001

Data Index: 1652887 (Python Code)

Max Activating Token Index: 181

Text #8

Max Range: 3.8275. Min Range: -3.8275

Max Act: 2.9813. Min Act: -0.0001

Data Index: 1422108 (Python Code)

Max Activating Token Index: 758

Text #9

Max Range: 3.8275. Min Range: -3.8275

Max Act: 2.9166. Min Act: -0.0001

Data Index: 1594864 (Python Code)

Max Activating Token Index: 664

Text #10

Max Range: 3.8275. Min Range: -3.8275

Max Act: 3.0415. Min Act: -0.0001

Data Index: 1385775 (Python Code)

Max Activating Token Index: 362

Text #11

Max Range: 3.8275. Min Range: -3.8275

Max Act: 2.7508. Min Act: -0.0001

Data Index: 1437323 (Python Code)

Max Activating Token Index: 25

Text #12

Max Range: 3.8275. Min Range: -3.8275

Max Act: 2.5628. Min Act: -0.0001

Data Index: 1408271 (Python Code)

Max Activating Token Index: 809

Text #13

Max Range: 3.8275. Min Range: -3.8275

Max Act: 2.6924. Min Act: -0.0001

Data Index: 1387327 (Python Code)

Max Activating Token Index: 63

Text #14

Max Range: 3.8275. Min Range: -3.8275

Max Act: 2.8261. Min Act: -0.0001

Data Index: 1609305 (Python Code)

Max Activating Token Index: 366

Text #15

Max Range: 3.8275. Min Range: -3.8275

Max Act: 3.2558. Min Act: -0.0001

Data Index: 1544317 (Python Code)

Max Activating Token Index: 763

Text #16

Max Range: 3.8275. Min Range: -3.8275

Max Act: 2.6620. Min Act: -0.0001

Data Index: 1627183 (Python Code)

Max Activating Token Index: 835

Text #17

Max Range: 3.8275. Min Range: -3.8275

Max Act: 2.6378. Min Act: -0.0001

Data Index: 1447123 (Python Code)

Max Activating Token Index: 16

Text #18

Max Range: 3.8275. Min Range: -3.8275

Max Act: 2.7689. Min Act: -0.0001

Data Index: 1416684 (Python Code)

Max Activating Token Index: 493

Text #19

Max Range: 3.8275. Min Range: -3.8275

Max Act: 2.6217. Min Act: -0.0001

Data Index: 1570548 (Python Code)

Max Activating Token Index: 705