Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3159 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0468. Min Act: -0.0002

Data Index: 1410241 (Python Code)

Max Activating Token Index: 120

Text #1

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0478. Min Act: -0.0003

Data Index: 1376223 (Python Code)

Max Activating Token Index: 179

Text #2

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0444. Min Act: -0.0003

Data Index: 1436687 (Python Code)

Max Activating Token Index: 847

Text #3

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0462. Min Act: -0.0003

Data Index: 1471936 (Python Code)

Max Activating Token Index: 778

Text #4

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0455. Min Act: -0.0003

Data Index: 1591649 (Python Code)

Max Activating Token Index: 743

Text #5

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0436. Min Act: -0.0003

Data Index: 1381611 (Python Code)

Max Activating Token Index: 77

Text #6

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0439. Min Act: -0.0002

Data Index: 1519220 (Python Code)

Max Activating Token Index: 365

Text #7

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0433. Min Act: -0.0002

Data Index: 1622170 (Python Code)

Max Activating Token Index: 487

Text #8

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0439. Min Act: -0.0002

Data Index: 1536818 (Python Code)

Max Activating Token Index: 425

Text #9

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0429. Min Act: -0.0003

Data Index: 1649054 (Python Code)

Max Activating Token Index: 242

Text #10

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0444. Min Act: -0.0003

Data Index: 1572105 (Python Code)

Max Activating Token Index: 28

Text #11

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0413. Min Act: -0.0002

Data Index: 1539679 (Python Code)

Max Activating Token Index: 322

Text #12

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0445. Min Act: -0.0002

Data Index: 1410606 (Python Code)

Max Activating Token Index: 153

Text #13

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0440. Min Act: -0.0002

Data Index: 1549773 (Python Code)

Max Activating Token Index: 495

Text #14

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0420. Min Act: -0.0003

Data Index: 1576179 (Python Code)

Max Activating Token Index: 863

Text #15

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0416. Min Act: -0.0002

Data Index: 1360280 (Python Code)

Max Activating Token Index: 526

Text #16

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0434. Min Act: -0.0002

Data Index: 1367387 (Python Code)

Max Activating Token Index: 111

Text #17

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0413. Min Act: -0.0002

Data Index: 1576120 (Python Code)

Max Activating Token Index: 186

Text #18

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0409. Min Act: -0.0002

Data Index: 1626504 (Python Code)

Max Activating Token Index: 295

Text #19

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0414. Min Act: -0.0002

Data Index: 1470067 (Python Code)

Max Activating Token Index: 524