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

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

Neuron 5473 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1623. Min Range: -1.1623

Max Act: 1.1623. Min Act: -0.0000

Data Index: 1400783 (Python Code)

Max Activating Token Index: 751

Text #1

Max Range: 1.1623. Min Range: -1.1623

Max Act: 1.1290. Min Act: -0.0000

Data Index: 1484196 (Python Code)

Max Activating Token Index: 158

Text #2

Max Range: 1.1623. Min Range: -1.1623

Max Act: 1.0628. Min Act: -0.0000

Data Index: 1390748 (Python Code)

Max Activating Token Index: 802

Text #3

Max Range: 1.1623. Min Range: -1.1623

Max Act: 1.0533. Min Act: -0.0000

Data Index: 1588632 (Python Code)

Max Activating Token Index: 426

Text #4

Max Range: 1.1623. Min Range: -1.1623

Max Act: 1.0547. Min Act: -0.0000

Data Index: 1615494 (Python Code)

Max Activating Token Index: 179

Text #5

Max Range: 1.1623. Min Range: -1.1623

Max Act: 1.0163. Min Act: -0.0000

Data Index: 1640292 (Python Code)

Max Activating Token Index: 962

Text #6

Max Range: 1.1623. Min Range: -1.1623

Max Act: 0.9262. Min Act: -0.0000

Data Index: 1522125 (Python Code)

Max Activating Token Index: 324

Text #7

Max Range: 1.1623. Min Range: -1.1623

Max Act: 0.9236. Min Act: -0.0000

Data Index: 1428225 (Python Code)

Max Activating Token Index: 207

Text #8

Max Range: 1.1623. Min Range: -1.1623

Max Act: 0.9435. Min Act: -0.0000

Data Index: 1495319 (Python Code)

Max Activating Token Index: 791

Text #9

Max Range: 1.1623. Min Range: -1.1623

Max Act: 0.9340. Min Act: -0.0000

Data Index: 1579820 (Python Code)

Max Activating Token Index: 353

Text #10

Max Range: 1.1623. Min Range: -1.1623

Max Act: 1.0074. Min Act: -0.0000

Data Index: 1575511 (Python Code)

Max Activating Token Index: 266

Text #11

Max Range: 1.1623. Min Range: -1.1623

Max Act: 0.8597. Min Act: -0.0000

Data Index: 1618294 (Python Code)

Max Activating Token Index: 365

Text #12

Max Range: 1.1623. Min Range: -1.1623

Max Act: 0.8497. Min Act: -0.0000

Data Index: 1508549 (Python Code)

Max Activating Token Index: 533

Text #13

Max Range: 1.1623. Min Range: -1.1623

Max Act: 0.8445. Min Act: -0.0000

Data Index: 1477123 (Python Code)

Max Activating Token Index: 472

Text #14

Max Range: 1.1623. Min Range: -1.1623

Max Act: 0.8856. Min Act: -0.0000

Data Index: 1493945 (Python Code)

Max Activating Token Index: 335

Text #15

Max Range: 1.1623. Min Range: -1.1623

Max Act: 0.8948. Min Act: -0.0000

Data Index: 1508669 (Python Code)

Max Activating Token Index: 947

Text #16

Max Range: 1.1623. Min Range: -1.1623

Max Act: 0.8750. Min Act: -0.0000

Data Index: 1627961 (Python Code)

Max Activating Token Index: 139

Text #17

Max Range: 1.1623. Min Range: -1.1623

Max Act: 0.8444. Min Act: -0.0000

Data Index: 1525001 (Python Code)

Max Activating Token Index: 701

Text #18

Max Range: 1.1623. Min Range: -1.1623

Max Act: 0.8598. Min Act: -0.0000

Data Index: 1588730 (Python Code)

Max Activating Token Index: 382

Text #19

Max Range: 1.1623. Min Range: -1.1623

Max Act: 0.8547. Min Act: -0.0000

Data Index: 1416649 (Python Code)

Max Activating Token Index: 701