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

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

Neuron 885 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4360. Min Range: -0.4360

Max Act: 0.4324. Min Act: -0.0001

Data Index: 1542012 (Python Code)

Max Activating Token Index: 40

Text #1

Max Range: 0.4360. Min Range: -0.4360

Max Act: 0.4360. Min Act: -0.0001

Data Index: 1489070 (Python Code)

Max Activating Token Index: 40

Text #2

Max Range: 0.4360. Min Range: -0.4360

Max Act: 0.4175. Min Act: -0.0001

Data Index: 1492106 (Python Code)

Max Activating Token Index: 42

Text #3

Max Range: 0.4360. Min Range: -0.4360

Max Act: 0.3893. Min Act: -0.0001

Data Index: 1648279 (Python Code)

Max Activating Token Index: 40

Text #4

Max Range: 0.4360. Min Range: -0.4360

Max Act: 0.3897. Min Act: -0.0001

Data Index: 1420336 (Python Code)

Max Activating Token Index: 33

Text #5

Max Range: 0.4360. Min Range: -0.4360

Max Act: 0.3837. Min Act: -0.0001

Data Index: 1610694 (Python Code)

Max Activating Token Index: 59

Text #6

Max Range: 0.4360. Min Range: -0.4360

Max Act: 0.3981. Min Act: -0.0001

Data Index: 1632690 (Python Code)

Max Activating Token Index: 49

Text #7

Max Range: 0.4360. Min Range: -0.4360

Max Act: 0.3962. Min Act: -0.0001

Data Index: 1577345 (Python Code)

Max Activating Token Index: 40

Text #8

Max Range: 0.4360. Min Range: -0.4360

Max Act: 0.3873. Min Act: -0.0001

Data Index: 1439221 (Python Code)

Max Activating Token Index: 32

Text #9

Max Range: 0.4360. Min Range: -0.4360

Max Act: 0.3825. Min Act: -0.0001

Data Index: 1492049 (Python Code)

Max Activating Token Index: 50

Text #10

Max Range: 0.4360. Min Range: -0.4360

Max Act: 0.3680. Min Act: -0.0001

Data Index: 1528500 (Python Code)

Max Activating Token Index: 34

Text #11

Max Range: 0.4360. Min Range: -0.4360

Max Act: 0.3633. Min Act: -0.0001

Data Index: 1615718 (Python Code)

Max Activating Token Index: 40

Text #12

Max Range: 0.4360. Min Range: -0.4360

Max Act: 0.3886. Min Act: -0.0001

Data Index: 1492109 (Python Code)

Max Activating Token Index: 50

Text #13

Max Range: 0.4360. Min Range: -0.4360

Max Act: 0.3573. Min Act: -0.0001

Data Index: 1593267 (Python Code)

Max Activating Token Index: 41

Text #14

Max Range: 0.4360. Min Range: -0.4360

Max Act: 0.3612. Min Act: -0.0001

Data Index: 1587070 (Python Code)

Max Activating Token Index: 41

Text #15

Max Range: 0.4360. Min Range: -0.4360

Max Act: 0.3553. Min Act: -0.0001

Data Index: 1560735 (Python Code)

Max Activating Token Index: 44

Text #16

Max Range: 0.4360. Min Range: -0.4360

Max Act: 0.3569. Min Act: -0.0001

Data Index: 1653778 (Python Code)

Max Activating Token Index: 43

Text #17

Max Range: 0.4360. Min Range: -0.4360

Max Act: 0.3716. Min Act: -0.0001

Data Index: 1626306 (Python Code)

Max Activating Token Index: 45

Text #18

Max Range: 0.4360. Min Range: -0.4360

Max Act: 0.3671. Min Act: -0.0001

Data Index: 1513095 (Python Code)

Max Activating Token Index: 105

Text #19

Max Range: 0.4360. Min Range: -0.4360

Max Act: 0.3703. Min Act: -0.0001

Data Index: 1558490 (Python Code)

Max Activating Token Index: 44