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

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

Neuron 2188 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.5454. Min Range: -1.5454

Max Act: 1.5454. Min Act: -0.0002

Data Index: 1378503 (Python Code)

Max Activating Token Index: 875

Text #1

Max Range: 1.5454. Min Range: -1.5454

Max Act: 1.4325. Min Act: -0.0002

Data Index: 1573398 (Python Code)

Max Activating Token Index: 66

Text #2

Max Range: 1.5454. Min Range: -1.5454

Max Act: 1.4610. Min Act: -0.0002

Data Index: 1638773 (Python Code)

Max Activating Token Index: 358

Text #3

Max Range: 1.5454. Min Range: -1.5454

Max Act: 1.4001. Min Act: -0.0002

Data Index: 1630227 (Python Code)

Max Activating Token Index: 914

Text #4

Max Range: 1.5454. Min Range: -1.5454

Max Act: 1.3935. Min Act: -0.0002

Data Index: 1482720 (Python Code)

Max Activating Token Index: 399

Text #5

Max Range: 1.5454. Min Range: -1.5454

Max Act: 1.3448. Min Act: -0.0002

Data Index: 1382308 (Python Code)

Max Activating Token Index: 389

Text #6

Max Range: 1.5454. Min Range: -1.5454

Max Act: 1.3494. Min Act: -0.0002

Data Index: 1407708 (Python Code)

Max Activating Token Index: 479

Text #7

Max Range: 1.5454. Min Range: -1.5454

Max Act: 1.3625. Min Act: -0.0002

Data Index: 1522788 (Python Code)

Max Activating Token Index: 922

Text #8

Max Range: 1.5454. Min Range: -1.5454

Max Act: 1.3476. Min Act: -0.0002

Data Index: 1372743 (Python Code)

Max Activating Token Index: 612

Text #9

Max Range: 1.5454. Min Range: -1.5454

Max Act: 1.3640. Min Act: -0.0002

Data Index: 1563333 (Python Code)

Max Activating Token Index: 10

Text #10

Max Range: 1.5454. Min Range: -1.5454

Max Act: 1.3260. Min Act: -0.0002

Data Index: 1525619 (Python Code)

Max Activating Token Index: 94

Text #11

Max Range: 1.5454. Min Range: -1.5454

Max Act: 1.2995. Min Act: -0.0002

Data Index: 1474756 (Python Code)

Max Activating Token Index: 460

Text #12

Max Range: 1.5454. Min Range: -1.5454

Max Act: 1.3244. Min Act: -0.0002

Data Index: 1514436 (Python Code)

Max Activating Token Index: 480

Text #13

Max Range: 1.5454. Min Range: -1.5454

Max Act: 1.2790. Min Act: -0.0002

Data Index: 1465409 (Python Code)

Max Activating Token Index: 189

Text #14

Max Range: 1.5454. Min Range: -1.5454

Max Act: 1.2790. Min Act: -0.0002

Data Index: 1441745 (Python Code)

Max Activating Token Index: 502

Text #15

Max Range: 1.5454. Min Range: -1.5454

Max Act: 1.3134. Min Act: -0.0002

Data Index: 1477663 (Python Code)

Max Activating Token Index: 894

Text #16

Max Range: 1.5454. Min Range: -1.5454

Max Act: 1.2890. Min Act: -0.0002

Data Index: 1448985 (Python Code)

Max Activating Token Index: 45

Text #17

Max Range: 1.5454. Min Range: -1.5454

Max Act: 1.2900. Min Act: -0.0002

Data Index: 1433190 (Python Code)

Max Activating Token Index: 29

Text #18

Max Range: 1.5454. Min Range: -1.5454

Max Act: 1.3445. Min Act: -0.0002

Data Index: 1583648 (Python Code)

Max Activating Token Index: 747

Text #19

Max Range: 1.5454. Min Range: -1.5454

Max Act: 1.2588. Min Act: -0.0002

Data Index: 1647002 (Python Code)

Max Activating Token Index: 32