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

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

Neuron 3675 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: 2.1867. Min Range: -2.1867

Max Act: 2.0629. Min Act: -0.0000

Data Index: 1376479 (Python Code)

Max Activating Token Index: 103

Text #1

Max Range: 2.1867. Min Range: -2.1867

Max Act: 2.1074. Min Act: -0.0000

Data Index: 1466503 (Python Code)

Max Activating Token Index: 466

Text #2

Max Range: 2.1867. Min Range: -2.1867

Max Act: 1.9732. Min Act: -0.0000

Data Index: 1509276 (Python Code)

Max Activating Token Index: 674

Text #3

Max Range: 2.1867. Min Range: -2.1867

Max Act: 2.1867. Min Act: -0.0000

Data Index: 1527539 (Python Code)

Max Activating Token Index: 155

Text #4

Max Range: 2.1867. Min Range: -2.1867

Max Act: 2.1062. Min Act: -0.0000

Data Index: 1476188 (Python Code)

Max Activating Token Index: 38

Text #5

Max Range: 2.1867. Min Range: -2.1867

Max Act: 1.8592. Min Act: -0.0000

Data Index: 1514228 (Python Code)

Max Activating Token Index: 306

Text #6

Max Range: 2.1867. Min Range: -2.1867

Max Act: 1.8633. Min Act: -0.0000

Data Index: 1612661 (Python Code)

Max Activating Token Index: 182

Text #7

Max Range: 2.1867. Min Range: -2.1867

Max Act: 1.8457. Min Act: -0.0000

Data Index: 1631567 (Python Code)

Max Activating Token Index: 686

Text #8

Max Range: 2.1867. Min Range: -2.1867

Max Act: 1.8229. Min Act: -0.0000

Data Index: 1469532 (Python Code)

Max Activating Token Index: 517

Text #9

Max Range: 2.1867. Min Range: -2.1867

Max Act: 1.9892. Min Act: -0.0000

Data Index: 1367508 (Python Code)

Max Activating Token Index: 477

Text #10

Max Range: 2.1867. Min Range: -2.1867

Max Act: 1.8239. Min Act: -0.0000

Data Index: 1602064 (Python Code)

Max Activating Token Index: 158

Text #11

Max Range: 2.1867. Min Range: -2.1867

Max Act: 1.8082. Min Act: -0.0000

Data Index: 1538271 (Python Code)

Max Activating Token Index: 800

Text #12

Max Range: 2.1867. Min Range: -2.1867

Max Act: 1.8007. Min Act: -0.0000

Data Index: 1450561 (Python Code)

Max Activating Token Index: 514

Text #13

Max Range: 2.1867. Min Range: -2.1867

Max Act: 1.7920. Min Act: -0.0000

Data Index: 1644208 (Python Code)

Max Activating Token Index: 298

Text #14

Max Range: 2.1867. Min Range: -2.1867

Max Act: 1.7612. Min Act: -0.0000

Data Index: 1470333 (Python Code)

Max Activating Token Index: 845

Text #15

Max Range: 2.1867. Min Range: -2.1867

Max Act: 1.7584. Min Act: -0.0000

Data Index: 1411871 (Python Code)

Max Activating Token Index: 906

Text #16

Max Range: 2.1867. Min Range: -2.1867

Max Act: 1.8594. Min Act: -0.0000

Data Index: 1397806 (Python Code)

Max Activating Token Index: 952

Text #17

Max Range: 2.1867. Min Range: -2.1867

Max Act: 1.7444. Min Act: -0.0000

Data Index: 1404501 (Python Code)

Max Activating Token Index: 218

Text #18

Max Range: 2.1867. Min Range: -2.1867

Max Act: 1.7278. Min Act: -0.0000

Data Index: 1531079 (Python Code)

Max Activating Token Index: 468

Text #19

Max Range: 2.1867. Min Range: -2.1867

Max Act: 1.6726. Min Act: -0.0000

Data Index: 1499330 (Python Code)

Max Activating Token Index: 423