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

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

Neuron 2384 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.9910. Min Act: 0.0000

Data Index: 1528883 (Python Code)

Max Activating Token Index: 353

Text #1

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.9685. Min Act: -0.0000

Data Index: 1647344 (Python Code)

Max Activating Token Index: 396

Text #2

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.9619. Min Act: -0.0000

Data Index: 1576495 (Python Code)

Max Activating Token Index: 451

Text #3

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.9112. Min Act: -0.0000

Data Index: 1609836 (Python Code)

Max Activating Token Index: 496

Text #4

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.8898. Min Act: -0.0000

Data Index: 1481170 (Python Code)

Max Activating Token Index: 411

Text #5

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.8738. Min Act: -0.0000

Data Index: 1460761 (Python Code)

Max Activating Token Index: 241

Text #6

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.9002. Min Act: -0.0000

Data Index: 1453345 (Python Code)

Max Activating Token Index: 581

Text #7

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.8700. Min Act: -0.0000

Data Index: 1465522 (Python Code)

Max Activating Token Index: 641

Text #8

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.8923. Min Act: -0.0000

Data Index: 1538731 (Python Code)

Max Activating Token Index: 457

Text #9

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.7936. Min Act: -0.0000

Data Index: 1646589 (Python Code)

Max Activating Token Index: 217

Text #10

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.8360. Min Act: -0.0000

Data Index: 1632649 (Python Code)

Max Activating Token Index: 608

Text #11

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.8493. Min Act: -0.0000

Data Index: 1615305 (Python Code)

Max Activating Token Index: 945

Text #12

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.8240. Min Act: -0.0000

Data Index: 1637223 (Python Code)

Max Activating Token Index: 952

Text #13

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.8535. Min Act: -0.0000

Data Index: 1420274 (Python Code)

Max Activating Token Index: 483

Text #14

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.8266. Min Act: -0.0000

Data Index: 1476757 (Python Code)

Max Activating Token Index: 133

Text #15

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.7988. Min Act: -0.0000

Data Index: 1652864 (Python Code)

Max Activating Token Index: 275

Text #16

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.7979. Min Act: 0.0000

Data Index: 1545830 (Python Code)

Max Activating Token Index: 44

Text #17

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.7882. Min Act: 0.0000

Data Index: 1614279 (Python Code)

Max Activating Token Index: 100

Text #18

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.7862. Min Act: -0.0000

Data Index: 1484643 (Python Code)

Max Activating Token Index: 511

Text #19

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.8123. Min Act: -0.0000

Data Index: 1574677 (Python Code)

Max Activating Token Index: 306