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

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

Neuron 1784 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2226. Min Range: -0.2226

Max Act: 0.2226. Min Act: -0.0003

Data Index: 1360855 (Python Code)

Max Activating Token Index: 58

Text #1

Max Range: 0.2226. Min Range: -0.2226

Max Act: 0.2170. Min Act: -0.0003

Data Index: 1496047 (Python Code)

Max Activating Token Index: 252

Text #2

Max Range: 0.2226. Min Range: -0.2226

Max Act: 0.2065. Min Act: -0.0003

Data Index: 1617797 (Python Code)

Max Activating Token Index: 161

Text #3

Max Range: 0.2226. Min Range: -0.2226

Max Act: 0.1989. Min Act: -0.0003

Data Index: 1641320 (Python Code)

Max Activating Token Index: 987

Text #4

Max Range: 0.2226. Min Range: -0.2226

Max Act: 0.2132. Min Act: -0.0003

Data Index: 1460929 (Python Code)

Max Activating Token Index: 576

Text #5

Max Range: 0.2226. Min Range: -0.2226

Max Act: 0.2125. Min Act: -0.0003

Data Index: 1307297 (C4 (Web Text))

Max Activating Token Index: 833

Text #6

Max Range: 0.2226. Min Range: -0.2226

Max Act: 0.2197. Min Act: -0.0003

Data Index: 1627810 (Python Code)

Max Activating Token Index: 103

Text #7

Max Range: 0.2226. Min Range: -0.2226

Max Act: 0.2069. Min Act: -0.0003

Data Index: 1376917 (Python Code)

Max Activating Token Index: 147

Text #8

Max Range: 0.2226. Min Range: -0.2226

Max Act: 0.2107. Min Act: -0.0003

Data Index: 1418340 (Python Code)

Max Activating Token Index: 588

Text #9

Max Range: 0.2226. Min Range: -0.2226

Max Act: 0.2127. Min Act: -0.0003

Data Index: 378439 (C4 (Web Text))

Max Activating Token Index: 484

Text #10

Max Range: 0.2226. Min Range: -0.2226

Max Act: 0.2042. Min Act: -0.0003

Data Index: 1444545 (Python Code)

Max Activating Token Index: 16

Text #11

Max Range: 0.2226. Min Range: -0.2226

Max Act: 0.2032. Min Act: -0.0003

Data Index: 1480861 (Python Code)

Max Activating Token Index: 115

Text #12

Max Range: 0.2226. Min Range: -0.2226

Max Act: 0.1783. Min Act: -0.0003

Data Index: 318129 (C4 (Web Text))

Max Activating Token Index: 694

Text #13

Max Range: 0.2226. Min Range: -0.2226

Max Act: 0.2018. Min Act: -0.0003

Data Index: 1597743 (Python Code)

Max Activating Token Index: 218

Text #14

Max Range: 0.2226. Min Range: -0.2226

Max Act: 0.2016. Min Act: -0.0003

Data Index: 196917 (C4 (Web Text))

Max Activating Token Index: 8

Text #15

Max Range: 0.2226. Min Range: -0.2226

Max Act: 0.2002. Min Act: -0.0003

Data Index: 1388516 (Python Code)

Max Activating Token Index: 31

Text #16

Max Range: 0.2226. Min Range: -0.2226

Max Act: 0.2063. Min Act: -0.0003

Data Index: 1476180 (Python Code)

Max Activating Token Index: 25

Text #17

Max Range: 0.2226. Min Range: -0.2226

Max Act: 0.1998. Min Act: -0.0003

Data Index: 242760 (C4 (Web Text))

Max Activating Token Index: 80

Text #18

Max Range: 0.2226. Min Range: -0.2226

Max Act: 0.2052. Min Act: -0.0003

Data Index: 1614424 (Python Code)

Max Activating Token Index: 769

Text #19

Max Range: 0.2226. Min Range: -0.2226

Max Act: 0.1986. Min Act: -0.0003

Data Index: 933611 (C4 (Web Text))

Max Activating Token Index: 446