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

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

Neuron 1234 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0738. Min Act: -0.0004

Data Index: 1491975 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0640. Min Act: -0.0004

Data Index: 1429446 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0625. Min Act: -0.0004

Data Index: 1641304 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0601. Min Act: -0.0004

Data Index: 1465539 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0652. Min Act: -0.0004

Data Index: 1556980 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0584. Min Act: -0.0004

Data Index: 1411581 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0579. Min Act: -0.0004

Data Index: 1549499 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0554. Min Act: -0.0004

Data Index: 1601753 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0528. Min Act: -0.0004

Data Index: 1544843 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0517. Min Act: -0.0004

Data Index: 1551769 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0552. Min Act: -0.0004

Data Index: 1545267 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0533. Min Act: -0.0004

Data Index: 1646854 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0499. Min Act: -0.0004

Data Index: 1033701 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0472. Min Act: -0.0004

Data Index: 1583275 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0485. Min Act: -0.0004

Data Index: 1466145 (Python Code)

Max Activating Token Index: 172

Text #15

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0466. Min Act: -0.0004

Data Index: 1190789 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0478. Min Act: -0.0004

Data Index: 1633517 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0478. Min Act: -0.0004

Data Index: 1571776 (Python Code)

Max Activating Token Index: 1023

Text #18

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0479. Min Act: -0.0004

Data Index: 1461078 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0480. Min Act: -0.0004

Data Index: 1589971 (Python Code)

Max Activating Token Index: 1023