Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1992 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.2186. Min Act: -0.0001

Data Index: 1517002 (Python Code)

Max Activating Token Index: 653

Text #1

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.1915. Min Act: -0.0001

Data Index: 1580511 (Python Code)

Max Activating Token Index: 345

Text #2

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.1863. Min Act: -0.0001

Data Index: 1475941 (Python Code)

Max Activating Token Index: 1004

Text #3

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.1675. Min Act: -0.0001

Data Index: 1423340 (Python Code)

Max Activating Token Index: 515

Text #4

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.1730. Min Act: -0.0001

Data Index: 1420498 (Python Code)

Max Activating Token Index: 345

Text #5

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.1730. Min Act: -0.0001

Data Index: 1460219 (Python Code)

Max Activating Token Index: 676

Text #6

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.1798. Min Act: -0.0001

Data Index: 1379849 (Python Code)

Max Activating Token Index: 624

Text #7

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.1591. Min Act: -0.0001

Data Index: 1596040 (Python Code)

Max Activating Token Index: 357

Text #8

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.1565. Min Act: -0.0001

Data Index: 1361095 (Python Code)

Max Activating Token Index: 976

Text #9

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.1545. Min Act: -0.0001

Data Index: 1644807 (Python Code)

Max Activating Token Index: 239

Text #10

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.1534. Min Act: -0.0001

Data Index: 1532157 (Python Code)

Max Activating Token Index: 439

Text #11

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.1730. Min Act: -0.0001

Data Index: 1557521 (Python Code)

Max Activating Token Index: 639

Text #12

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.1527. Min Act: -0.0001

Data Index: 694053 (C4 (Web Text))

Max Activating Token Index: 791

Text #13

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.1476. Min Act: -0.0001

Data Index: 1395073 (Python Code)

Max Activating Token Index: 867

Text #14

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.1465. Min Act: -0.0001

Data Index: 1438215 (Python Code)

Max Activating Token Index: 461

Text #15

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.1509. Min Act: -0.0001

Data Index: 1577056 (Python Code)

Max Activating Token Index: 862

Text #16

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.1556. Min Act: -0.0001

Data Index: 1467526 (Python Code)

Max Activating Token Index: 65

Text #17

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.1501. Min Act: -0.0001

Data Index: 1472664 (Python Code)

Max Activating Token Index: 67

Text #18

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.1492. Min Act: -0.0001

Data Index: 1563795 (Python Code)

Max Activating Token Index: 471

Text #19

Max Range: 0.2186. Min Range: -0.2186

Max Act: 0.1491. Min Act: -0.0001

Data Index: 1629784 (Python Code)

Max Activating Token Index: 128