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

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

Neuron 1081 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8360. Min Range: -1.8360

Max Act: 1.8360. Min Act: -0.0002

Data Index: 1389756 (Python Code)

Max Activating Token Index: 186

Text #1

Max Range: 1.8360. Min Range: -1.8360

Max Act: 1.6164. Min Act: -0.0002

Data Index: 1441824 (Python Code)

Max Activating Token Index: 190

Text #2

Max Range: 1.8360. Min Range: -1.8360

Max Act: 1.6622. Min Act: -0.0002

Data Index: 1555231 (Python Code)

Max Activating Token Index: 133

Text #3

Max Range: 1.8360. Min Range: -1.8360

Max Act: 1.6449. Min Act: -0.0002

Data Index: 1571550 (Python Code)

Max Activating Token Index: 148

Text #4

Max Range: 1.8360. Min Range: -1.8360

Max Act: 1.6516. Min Act: -0.0002

Data Index: 1648561 (Python Code)

Max Activating Token Index: 40

Text #5

Max Range: 1.8360. Min Range: -1.8360

Max Act: 1.5682. Min Act: -0.0002

Data Index: 1449216 (Python Code)

Max Activating Token Index: 73

Text #6

Max Range: 1.8360. Min Range: -1.8360

Max Act: 1.6354. Min Act: -0.0002

Data Index: 1410136 (Python Code)

Max Activating Token Index: 121

Text #7

Max Range: 1.8360. Min Range: -1.8360

Max Act: 1.6577. Min Act: -0.0002

Data Index: 1515022 (Python Code)

Max Activating Token Index: 140

Text #8

Max Range: 1.8360. Min Range: -1.8360

Max Act: 1.5020. Min Act: -0.0002

Data Index: 1635724 (Python Code)

Max Activating Token Index: 202

Text #9

Max Range: 1.8360. Min Range: -1.8360

Max Act: 1.5566. Min Act: -0.0002

Data Index: 1548914 (Python Code)

Max Activating Token Index: 285

Text #10

Max Range: 1.8360. Min Range: -1.8360

Max Act: 1.5906. Min Act: -0.0002

Data Index: 1629081 (Python Code)

Max Activating Token Index: 13

Text #11

Max Range: 1.8360. Min Range: -1.8360

Max Act: 1.5841. Min Act: -0.0002

Data Index: 1587109 (Python Code)

Max Activating Token Index: 170

Text #12

Max Range: 1.8360. Min Range: -1.8360

Max Act: 1.5457. Min Act: -0.0002

Data Index: 1643052 (Python Code)

Max Activating Token Index: 19

Text #13

Max Range: 1.8360. Min Range: -1.8360

Max Act: 1.3911. Min Act: -0.0002

Data Index: 1525563 (Python Code)

Max Activating Token Index: 254

Text #14

Max Range: 1.8360. Min Range: -1.8360

Max Act: 1.5771. Min Act: -0.0002

Data Index: 1568893 (Python Code)

Max Activating Token Index: 268

Text #15

Max Range: 1.8360. Min Range: -1.8360

Max Act: 1.5772. Min Act: -0.0002

Data Index: 1615347 (Python Code)

Max Activating Token Index: 21

Text #16

Max Range: 1.8360. Min Range: -1.8360

Max Act: 1.6124. Min Act: -0.0002

Data Index: 1488955 (Python Code)

Max Activating Token Index: 144

Text #17

Max Range: 1.8360. Min Range: -1.8360

Max Act: 1.5639. Min Act: -0.0002

Data Index: 1607715 (Python Code)

Max Activating Token Index: 118

Text #18

Max Range: 1.8360. Min Range: -1.8360

Max Act: 1.4424. Min Act: -0.0002

Data Index: 1407847 (Python Code)

Max Activating Token Index: 190

Text #19

Max Range: 1.8360. Min Range: -1.8360

Max Act: 1.5583. Min Act: -0.0002

Data Index: 1394444 (Python Code)

Max Activating Token Index: 27