Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5476 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.7121. Min Range: -2.7121

Max Act: 2.7121. Min Act: -0.0001

Data Index: 1513862 (Python Code)

Max Activating Token Index: 105

Text #1

Max Range: 2.7121. Min Range: -2.7121

Max Act: 2.1093. Min Act: -0.0000

Data Index: 1551906 (Python Code)

Max Activating Token Index: 61

Text #2

Max Range: 2.7121. Min Range: -2.7121

Max Act: 2.0536. Min Act: -0.0000

Data Index: 1557603 (Python Code)

Max Activating Token Index: 909

Text #3

Max Range: 2.7121. Min Range: -2.7121

Max Act: 2.2797. Min Act: -0.0000

Data Index: 1590104 (Python Code)

Max Activating Token Index: 99

Text #4

Max Range: 2.7121. Min Range: -2.7121

Max Act: 1.9352. Min Act: -0.0000

Data Index: 1482768 (Python Code)

Max Activating Token Index: 62

Text #5

Max Range: 2.7121. Min Range: -2.7121

Max Act: 1.9241. Min Act: -0.0000

Data Index: 1517607 (Python Code)

Max Activating Token Index: 79

Text #6

Max Range: 2.7121. Min Range: -2.7121

Max Act: 1.8930. Min Act: -0.0000

Data Index: 1505617 (Python Code)

Max Activating Token Index: 756

Text #7

Max Range: 2.7121. Min Range: -2.7121

Max Act: 1.8498. Min Act: -0.0000

Data Index: 1564428 (Python Code)

Max Activating Token Index: 202

Text #8

Max Range: 2.7121. Min Range: -2.7121

Max Act: 1.8085. Min Act: -0.0000

Data Index: 1600553 (Python Code)

Max Activating Token Index: 43

Text #9

Max Range: 2.7121. Min Range: -2.7121

Max Act: 1.7268. Min Act: -0.0000

Data Index: 1623177 (Python Code)

Max Activating Token Index: 61

Text #10

Max Range: 2.7121. Min Range: -2.7121

Max Act: 1.6290. Min Act: -0.0000

Data Index: 1518886 (Python Code)

Max Activating Token Index: 105

Text #11

Max Range: 2.7121. Min Range: -2.7121

Max Act: 1.6122. Min Act: -0.0001

Data Index: 1606009 (Python Code)

Max Activating Token Index: 918

Text #12

Max Range: 2.7121. Min Range: -2.7121

Max Act: 1.4975. Min Act: -0.0000

Data Index: 1646047 (Python Code)

Max Activating Token Index: 849

Text #13

Max Range: 2.7121. Min Range: -2.7121

Max Act: 1.8368. Min Act: -0.0000

Data Index: 1521257 (Python Code)

Max Activating Token Index: 322

Text #14

Max Range: 2.7121. Min Range: -2.7121

Max Act: 1.5422. Min Act: -0.0000

Data Index: 1546267 (Python Code)

Max Activating Token Index: 582

Text #15

Max Range: 2.7121. Min Range: -2.7121

Max Act: 1.5738. Min Act: -0.0001

Data Index: 475289 (C4 (Web Text))

Max Activating Token Index: 124

Text #16

Max Range: 2.7121. Min Range: -2.7121

Max Act: 1.5716. Min Act: -0.0000

Data Index: 656186 (C4 (Web Text))

Max Activating Token Index: 21

Text #17

Max Range: 2.7121. Min Range: -2.7121

Max Act: 1.3014. Min Act: -0.0000

Data Index: 636471 (C4 (Web Text))

Max Activating Token Index: 654

Text #18

Max Range: 2.7121. Min Range: -2.7121

Max Act: 1.4042. Min Act: -0.0000

Data Index: 1360469 (Python Code)

Max Activating Token Index: 179

Text #19

Max Range: 2.7121. Min Range: -2.7121

Max Act: 1.3953. Min Act: -0.0001

Data Index: 57171 (C4 (Web Text))

Max Activating Token Index: 946