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

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

Neuron 3501 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: 0.2238. Min Range: -0.2238

Max Act: 0.2238. Min Act: -0.0001

Data Index: 1485410 (Python Code)

Max Activating Token Index: 248

Text #1

Max Range: 0.2238. Min Range: -0.2238

Max Act: 0.2188. Min Act: -0.0001

Data Index: 1368452 (Python Code)

Max Activating Token Index: 155

Text #2

Max Range: 0.2238. Min Range: -0.2238

Max Act: 0.2156. Min Act: -0.0000

Data Index: 1553101 (Python Code)

Max Activating Token Index: 841

Text #3

Max Range: 0.2238. Min Range: -0.2238

Max Act: 0.2140. Min Act: -0.0001

Data Index: 1581809 (Python Code)

Max Activating Token Index: 177

Text #4

Max Range: 0.2238. Min Range: -0.2238

Max Act: 0.2026. Min Act: -0.0001

Data Index: 1558141 (Python Code)

Max Activating Token Index: 156

Text #5

Max Range: 0.2238. Min Range: -0.2238

Max Act: 0.2019. Min Act: -0.0001

Data Index: 1452402 (Python Code)

Max Activating Token Index: 61

Text #6

Max Range: 0.2238. Min Range: -0.2238

Max Act: 0.2026. Min Act: -0.0001

Data Index: 1393104 (Python Code)

Max Activating Token Index: 89

Text #7

Max Range: 0.2238. Min Range: -0.2238

Max Act: 0.2013. Min Act: -0.0001

Data Index: 1547705 (Python Code)

Max Activating Token Index: 134

Text #8

Max Range: 0.2238. Min Range: -0.2238

Max Act: 0.2008. Min Act: -0.0001

Data Index: 1409754 (Python Code)

Max Activating Token Index: 461

Text #9

Max Range: 0.2238. Min Range: -0.2238

Max Act: 0.1983. Min Act: -0.0001

Data Index: 1496794 (Python Code)

Max Activating Token Index: 114

Text #10

Max Range: 0.2238. Min Range: -0.2238

Max Act: 0.1970. Min Act: -0.0001

Data Index: 1413901 (Python Code)

Max Activating Token Index: 686

Text #11

Max Range: 0.2238. Min Range: -0.2238

Max Act: 0.1966. Min Act: -0.0001

Data Index: 1555403 (Python Code)

Max Activating Token Index: 187

Text #12

Max Range: 0.2238. Min Range: -0.2238

Max Act: 0.1892. Min Act: -0.0001

Data Index: 1481182 (Python Code)

Max Activating Token Index: 758

Text #13

Max Range: 0.2238. Min Range: -0.2238

Max Act: 0.1885. Min Act: -0.0001

Data Index: 1533748 (Python Code)

Max Activating Token Index: 1019

Text #14

Max Range: 0.2238. Min Range: -0.2238

Max Act: 0.2006. Min Act: -0.0001

Data Index: 1361252 (Python Code)

Max Activating Token Index: 286

Text #15

Max Range: 0.2238. Min Range: -0.2238

Max Act: 0.2009. Min Act: -0.0000

Data Index: 1616347 (Python Code)

Max Activating Token Index: 161

Text #16

Max Range: 0.2238. Min Range: -0.2238

Max Act: 0.1917. Min Act: -0.0000

Data Index: 1539260 (Python Code)

Max Activating Token Index: 178

Text #17

Max Range: 0.2238. Min Range: -0.2238

Max Act: 0.1896. Min Act: -0.0001

Data Index: 1608922 (Python Code)

Max Activating Token Index: 314

Text #18

Max Range: 0.2238. Min Range: -0.2238

Max Act: 0.1893. Min Act: -0.0001

Data Index: 1387801 (Python Code)

Max Activating Token Index: 69

Text #19

Max Range: 0.2238. Min Range: -0.2238

Max Act: 0.1689. Min Act: -0.0000

Data Index: 1598728 (Python Code)

Max Activating Token Index: 819