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

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

Neuron 2104 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0185. Min Act: -0.0002

Data Index: 1647344 (Python Code)

Max Activating Token Index: 14

Text #1

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0172. Min Act: -0.0002

Data Index: 1571039 (Python Code)

Max Activating Token Index: 28

Text #2

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0158. Min Act: -0.0002

Data Index: 1414031 (Python Code)

Max Activating Token Index: 9

Text #3

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0162. Min Act: -0.0002

Data Index: 1385851 (Python Code)

Max Activating Token Index: 26

Text #4

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0149. Min Act: -0.0002

Data Index: 1647144 (Python Code)

Max Activating Token Index: 17

Text #5

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0150. Min Act: -0.0002

Data Index: 1424045 (Python Code)

Max Activating Token Index: 69

Text #6

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0144. Min Act: -0.0002

Data Index: 1472064 (Python Code)

Max Activating Token Index: 35

Text #7

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0146. Min Act: -0.0002

Data Index: 1407767 (Python Code)

Max Activating Token Index: 43

Text #8

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0151. Min Act: -0.0002

Data Index: 1630045 (Python Code)

Max Activating Token Index: 42

Text #9

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0147. Min Act: -0.0002

Data Index: 1621239 (Python Code)

Max Activating Token Index: 50

Text #10

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0141. Min Act: -0.0002

Data Index: 1538175 (Python Code)

Max Activating Token Index: 82

Text #11

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0141. Min Act: -0.0002

Data Index: 1389059 (Python Code)

Max Activating Token Index: 79

Text #12

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0140. Min Act: -0.0002

Data Index: 1501057 (Python Code)

Max Activating Token Index: 38

Text #13

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0140. Min Act: -0.0002

Data Index: 1446817 (Python Code)

Max Activating Token Index: 906

Text #14

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0138. Min Act: -0.0002

Data Index: 1570265 (Python Code)

Max Activating Token Index: 28

Text #15

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0140. Min Act: -0.0002

Data Index: 1627905 (Python Code)

Max Activating Token Index: 22

Text #16

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0141. Min Act: -0.0002

Data Index: 1523992 (Python Code)

Max Activating Token Index: 17

Text #17

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0138. Min Act: -0.0002

Data Index: 1483474 (Python Code)

Max Activating Token Index: 7

Text #18

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0134. Min Act: -0.0002

Data Index: 1398437 (Python Code)

Max Activating Token Index: 10

Text #19

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0139. Min Act: -0.0002

Data Index: 1566183 (Python Code)

Max Activating Token Index: 43