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

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

Neuron 2861 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: 0.0715. Min Range: -0.0715

Max Act: 0.0701. Min Act: -0.0004

Data Index: 1565968 (Python Code)

Max Activating Token Index: 39

Text #1

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0701. Min Act: -0.0004

Data Index: 1489340 (Python Code)

Max Activating Token Index: 45

Text #2

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0701. Min Act: -0.0004

Data Index: 1625850 (Python Code)

Max Activating Token Index: 145

Text #3

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0667. Min Act: -0.0004

Data Index: 1566415 (Python Code)

Max Activating Token Index: 885

Text #4

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0715. Min Act: -0.0004

Data Index: 1532784 (Python Code)

Max Activating Token Index: 31

Text #5

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0680. Min Act: -0.0004

Data Index: 1490675 (Python Code)

Max Activating Token Index: 939

Text #6

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0682. Min Act: -0.0004

Data Index: 1607734 (Python Code)

Max Activating Token Index: 244

Text #7

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0681. Min Act: -0.0004

Data Index: 1597251 (Python Code)

Max Activating Token Index: 20

Text #8

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0649. Min Act: -0.0004

Data Index: 1609612 (Python Code)

Max Activating Token Index: 994

Text #9

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0647. Min Act: -0.0004

Data Index: 1629495 (Python Code)

Max Activating Token Index: 120

Text #10

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0678. Min Act: -0.0004

Data Index: 1436433 (Python Code)

Max Activating Token Index: 284

Text #11

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0695. Min Act: -0.0004

Data Index: 1406175 (Python Code)

Max Activating Token Index: 80

Text #12

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0642. Min Act: -0.0004

Data Index: 1593348 (Python Code)

Max Activating Token Index: 91

Text #13

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0696. Min Act: -0.0004

Data Index: 1528053 (Python Code)

Max Activating Token Index: 96

Text #14

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0640. Min Act: -0.0004

Data Index: 1449561 (Python Code)

Max Activating Token Index: 378

Text #15

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0662. Min Act: -0.0004

Data Index: 1497759 (Python Code)

Max Activating Token Index: 923

Text #16

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0604. Min Act: -0.0004

Data Index: 1366175 (Python Code)

Max Activating Token Index: 829

Text #17

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0660. Min Act: -0.0004

Data Index: 1408765 (Python Code)

Max Activating Token Index: 947

Text #18

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0628. Min Act: -0.0004

Data Index: 1432597 (Python Code)

Max Activating Token Index: 45

Text #19

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0663. Min Act: -0.0004

Data Index: 1499422 (Python Code)

Max Activating Token Index: 909