Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1520 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.8125. Min Range: -1.8125

Max Act: 1.8125. Min Act: -0.0000

Data Index: 1599650 (Python Code)

Max Activating Token Index: 30

Text #1

Max Range: 1.8125. Min Range: -1.8125

Max Act: 1.6433. Min Act: -0.0000

Data Index: 1562915 (Python Code)

Max Activating Token Index: 28

Text #2

Max Range: 1.8125. Min Range: -1.8125

Max Act: 1.6792. Min Act: -0.0000

Data Index: 1626318 (Python Code)

Max Activating Token Index: 51

Text #3

Max Range: 1.8125. Min Range: -1.8125

Max Act: 1.5895. Min Act: -0.0001

Data Index: 1379349 (Python Code)

Max Activating Token Index: 44

Text #4

Max Range: 1.8125. Min Range: -1.8125

Max Act: 1.6078. Min Act: -0.0000

Data Index: 1597068 (Python Code)

Max Activating Token Index: 23

Text #5

Max Range: 1.8125. Min Range: -1.8125

Max Act: 1.5662. Min Act: -0.0000

Data Index: 1397500 (Python Code)

Max Activating Token Index: 181

Text #6

Max Range: 1.8125. Min Range: -1.8125

Max Act: 1.5622. Min Act: -0.0000

Data Index: 1612586 (Python Code)

Max Activating Token Index: 155

Text #7

Max Range: 1.8125. Min Range: -1.8125

Max Act: 1.4667. Min Act: -0.0000

Data Index: 1613025 (Python Code)

Max Activating Token Index: 258

Text #8

Max Range: 1.8125. Min Range: -1.8125

Max Act: 1.4110. Min Act: -0.0001

Data Index: 1035374 (C4 (Web Text))

Max Activating Token Index: 970

Text #9

Max Range: 1.8125. Min Range: -1.8125

Max Act: 1.4370. Min Act: -0.0000

Data Index: 1403295 (Python Code)

Max Activating Token Index: 100

Text #10

Max Range: 1.8125. Min Range: -1.8125

Max Act: 1.4285. Min Act: -0.0000

Data Index: 1493192 (Python Code)

Max Activating Token Index: 151

Text #11

Max Range: 1.8125. Min Range: -1.8125

Max Act: 1.5163. Min Act: -0.0001

Data Index: 1412802 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 1.8125. Min Range: -1.8125

Max Act: 1.4297. Min Act: -0.0000

Data Index: 1611878 (Python Code)

Max Activating Token Index: 197

Text #13

Max Range: 1.8125. Min Range: -1.8125

Max Act: 1.4672. Min Act: -0.0001

Data Index: 1611495 (Python Code)

Max Activating Token Index: 45

Text #14

Max Range: 1.8125. Min Range: -1.8125

Max Act: 1.3904. Min Act: -0.0000

Data Index: 1518681 (Python Code)

Max Activating Token Index: 159

Text #15

Max Range: 1.8125. Min Range: -1.8125

Max Act: 1.4368. Min Act: -0.0001

Data Index: 1365923 (Python Code)

Max Activating Token Index: 26

Text #16

Max Range: 1.8125. Min Range: -1.8125

Max Act: 1.4201. Min Act: -0.0001

Data Index: 1404725 (Python Code)

Max Activating Token Index: 21

Text #17

Max Range: 1.8125. Min Range: -1.8125

Max Act: 1.3030. Min Act: -0.0000

Data Index: 1572603 (Python Code)

Max Activating Token Index: 236

Text #18

Max Range: 1.8125. Min Range: -1.8125

Max Act: 1.4164. Min Act: -0.0001

Data Index: 1557954 (Python Code)

Max Activating Token Index: 46

Text #19

Max Range: 1.8125. Min Range: -1.8125

Max Act: 1.3644. Min Act: -0.0000

Data Index: 1417482 (Python Code)

Max Activating Token Index: 445