Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2226 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7646. Min Range: -0.7646

Max Act: 0.7646. Min Act: -0.0001

Data Index: 1504573 (Python Code)

Max Activating Token Index: 15

Text #1

Max Range: 0.7646. Min Range: -0.7646

Max Act: 0.7217. Min Act: -0.0001

Data Index: 1445700 (Python Code)

Max Activating Token Index: 444

Text #2

Max Range: 0.7646. Min Range: -0.7646

Max Act: 0.6145. Min Act: -0.0001

Data Index: 1579326 (Python Code)

Max Activating Token Index: 281

Text #3

Max Range: 0.7646. Min Range: -0.7646

Max Act: 0.6231. Min Act: -0.0001

Data Index: 1402733 (Python Code)

Max Activating Token Index: 3

Text #4

Max Range: 0.7646. Min Range: -0.7646

Max Act: 0.6035. Min Act: -0.0001

Data Index: 1564096 (Python Code)

Max Activating Token Index: 771

Text #5

Max Range: 0.7646. Min Range: -0.7646

Max Act: 0.6460. Min Act: -0.0001

Data Index: 1636451 (Python Code)

Max Activating Token Index: 4

Text #6

Max Range: 0.7646. Min Range: -0.7646

Max Act: 0.6160. Min Act: -0.0001

Data Index: 1449590 (Python Code)

Max Activating Token Index: 7

Text #7

Max Range: 0.7646. Min Range: -0.7646

Max Act: 0.5934. Min Act: -0.0001

Data Index: 1529095 (Python Code)

Max Activating Token Index: 891

Text #8

Max Range: 0.7646. Min Range: -0.7646

Max Act: 0.5866. Min Act: -0.0001

Data Index: 1633976 (Python Code)

Max Activating Token Index: 56

Text #9

Max Range: 0.7646. Min Range: -0.7646

Max Act: 0.6016. Min Act: -0.0001

Data Index: 1469274 (Python Code)

Max Activating Token Index: 953

Text #10

Max Range: 0.7646. Min Range: -0.7646

Max Act: 0.6080. Min Act: -0.0001

Data Index: 1583892 (Python Code)

Max Activating Token Index: 980

Text #11

Max Range: 0.7646. Min Range: -0.7646

Max Act: 0.5186. Min Act: -0.0001

Data Index: 1430628 (Python Code)

Max Activating Token Index: 158

Text #12

Max Range: 0.7646. Min Range: -0.7646

Max Act: 0.5236. Min Act: -0.0001

Data Index: 1406447 (Python Code)

Max Activating Token Index: 141

Text #13

Max Range: 0.7646. Min Range: -0.7646

Max Act: 0.5605. Min Act: -0.0001

Data Index: 1442552 (Python Code)

Max Activating Token Index: 1004

Text #14

Max Range: 0.7646. Min Range: -0.7646

Max Act: 0.5609. Min Act: -0.0001

Data Index: 1628868 (Python Code)

Max Activating Token Index: 479

Text #15

Max Range: 0.7646. Min Range: -0.7646

Max Act: 0.5416. Min Act: -0.0001

Data Index: 1539293 (Python Code)

Max Activating Token Index: 57

Text #16

Max Range: 0.7646. Min Range: -0.7646

Max Act: 0.5852. Min Act: -0.0001

Data Index: 1617169 (Python Code)

Max Activating Token Index: 143

Text #17

Max Range: 0.7646. Min Range: -0.7646

Max Act: 0.5264. Min Act: -0.0001

Data Index: 1420735 (Python Code)

Max Activating Token Index: 109

Text #18

Max Range: 0.7646. Min Range: -0.7646

Max Act: 0.5619. Min Act: -0.0001

Data Index: 1562405 (Python Code)

Max Activating Token Index: 3

Text #19

Max Range: 0.7646. Min Range: -0.7646

Max Act: 0.5454. Min Act: -0.0001

Data Index: 1490610 (Python Code)

Max Activating Token Index: 701