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

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

Neuron 2329 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3581. Min Range: -4.3581

Max Act: 4.3581. Min Act: -0.0000

Data Index: 1413582 (Python Code)

Max Activating Token Index: 320

Text #1

Max Range: 4.3581. Min Range: -4.3581

Max Act: 4.3578. Min Act: -0.0000

Data Index: 1597376 (Python Code)

Max Activating Token Index: 588

Text #2

Max Range: 4.3581. Min Range: -4.3581

Max Act: 4.0788. Min Act: -0.0000

Data Index: 1438205 (Python Code)

Max Activating Token Index: 376

Text #3

Max Range: 4.3581. Min Range: -4.3581

Max Act: 3.9822. Min Act: -0.0000

Data Index: 1384540 (Python Code)

Max Activating Token Index: 94

Text #4

Max Range: 4.3581. Min Range: -4.3581

Max Act: 3.6839. Min Act: -0.0000

Data Index: 1529719 (Python Code)

Max Activating Token Index: 342

Text #5

Max Range: 4.3581. Min Range: -4.3581

Max Act: 3.6812. Min Act: -0.0000

Data Index: 1558638 (Python Code)

Max Activating Token Index: 520

Text #6

Max Range: 4.3581. Min Range: -4.3581

Max Act: 3.7975. Min Act: -0.0000

Data Index: 1433439 (Python Code)

Max Activating Token Index: 279

Text #7

Max Range: 4.3581. Min Range: -4.3581

Max Act: 3.6119. Min Act: -0.0000

Data Index: 1418353 (Python Code)

Max Activating Token Index: 78

Text #8

Max Range: 4.3581. Min Range: -4.3581

Max Act: 3.7133. Min Act: -0.0000

Data Index: 1387524 (Python Code)

Max Activating Token Index: 817

Text #9

Max Range: 4.3581. Min Range: -4.3581

Max Act: 3.6183. Min Act: -0.0000

Data Index: 1495121 (Python Code)

Max Activating Token Index: 834

Text #10

Max Range: 4.3581. Min Range: -4.3581

Max Act: 3.4705. Min Act: -0.0000

Data Index: 1627555 (Python Code)

Max Activating Token Index: 899

Text #11

Max Range: 4.3581. Min Range: -4.3581

Max Act: 2.9203. Min Act: -0.0000

Data Index: 1490318 (Python Code)

Max Activating Token Index: 81

Text #12

Max Range: 4.3581. Min Range: -4.3581

Max Act: 3.1997. Min Act: -0.0000

Data Index: 1584868 (Python Code)

Max Activating Token Index: 855

Text #13

Max Range: 4.3581. Min Range: -4.3581

Max Act: 2.8898. Min Act: -0.0000

Data Index: 1461329 (Python Code)

Max Activating Token Index: 676

Text #14

Max Range: 4.3581. Min Range: -4.3581

Max Act: 2.9553. Min Act: -0.0000

Data Index: 1624109 (Python Code)

Max Activating Token Index: 946

Text #15

Max Range: 4.3581. Min Range: -4.3581

Max Act: 3.0529. Min Act: -0.0000

Data Index: 1592427 (Python Code)

Max Activating Token Index: 993

Text #16

Max Range: 4.3581. Min Range: -4.3581

Max Act: 2.7348. Min Act: -0.0000

Data Index: 1602692 (Python Code)

Max Activating Token Index: 979

Text #17

Max Range: 4.3581. Min Range: -4.3581

Max Act: 2.8411. Min Act: -0.0000

Data Index: 1471775 (Python Code)

Max Activating Token Index: 15

Text #18

Max Range: 4.3581. Min Range: -4.3581

Max Act: 2.6776. Min Act: -0.0000

Data Index: 1621171 (Python Code)

Max Activating Token Index: 376

Text #19

Max Range: 4.3581. Min Range: -4.3581

Max Act: 2.5372. Min Act: -0.0000

Data Index: 1451712 (Python Code)

Max Activating Token Index: 1022