Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2503 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.2109. Min Act: -0.0004

Data Index: 507787 (C4 (Web Text))

Max Activating Token Index: 881

Text #1

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.2002. Min Act: -0.0004

Data Index: 847740 (C4 (Web Text))

Max Activating Token Index: 347

Text #2

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.1783. Min Act: -0.0004

Data Index: 293301 (C4 (Web Text))

Max Activating Token Index: 368

Text #3

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.1594. Min Act: -0.0004

Data Index: 298467 (C4 (Web Text))

Max Activating Token Index: 623

Text #4

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.1775. Min Act: -0.0004

Data Index: 206245 (C4 (Web Text))

Max Activating Token Index: 884

Text #5

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.1835. Min Act: -0.0004

Data Index: 22037 (C4 (Web Text))

Max Activating Token Index: 113

Text #6

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.1712. Min Act: -0.0004

Data Index: 564684 (C4 (Web Text))

Max Activating Token Index: 770

Text #7

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.1705. Min Act: -0.0004

Data Index: 112555 (C4 (Web Text))

Max Activating Token Index: 96

Text #8

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.1642. Min Act: -0.0004

Data Index: 121613 (C4 (Web Text))

Max Activating Token Index: 501

Text #9

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.1748. Min Act: -0.0004

Data Index: 167193 (C4 (Web Text))

Max Activating Token Index: 53

Text #10

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.1396. Min Act: -0.0004

Data Index: 482650 (C4 (Web Text))

Max Activating Token Index: 985

Text #11

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.1735. Min Act: -0.0004

Data Index: 170268 (C4 (Web Text))

Max Activating Token Index: 468

Text #12

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.1846. Min Act: -0.0004

Data Index: 223472 (C4 (Web Text))

Max Activating Token Index: 384

Text #13

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.1700. Min Act: -0.0004

Data Index: 859891 (C4 (Web Text))

Max Activating Token Index: 125

Text #14

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.1757. Min Act: -0.0004

Data Index: 237078 (C4 (Web Text))

Max Activating Token Index: 503

Text #15

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.1681. Min Act: -0.0004

Data Index: 938176 (C4 (Web Text))

Max Activating Token Index: 179

Text #16

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.1563. Min Act: -0.0004

Data Index: 14437 (C4 (Web Text))

Max Activating Token Index: 153

Text #17

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.1679. Min Act: -0.0004

Data Index: 781497 (C4 (Web Text))

Max Activating Token Index: 137

Text #18

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.1673. Min Act: -0.0004

Data Index: 478029 (C4 (Web Text))

Max Activating Token Index: 109

Text #19

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.1598. Min Act: -0.0004

Data Index: 288579 (C4 (Web Text))

Max Activating Token Index: 253