Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1105 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.2332. Min Range: -0.2332

Max Act: 0.2332. Min Act: -0.0003

Data Index: 1451519 (Python Code)

Max Activating Token Index: 449

Text #1

Max Range: 0.2332. Min Range: -0.2332

Max Act: 0.2225. Min Act: -0.0003

Data Index: 1452495 (Python Code)

Max Activating Token Index: 570

Text #2

Max Range: 0.2332. Min Range: -0.2332

Max Act: 0.2229. Min Act: -0.0003

Data Index: 1554758 (Python Code)

Max Activating Token Index: 267

Text #3

Max Range: 0.2332. Min Range: -0.2332

Max Act: 0.2251. Min Act: -0.0003

Data Index: 1564315 (Python Code)

Max Activating Token Index: 123

Text #4

Max Range: 0.2332. Min Range: -0.2332

Max Act: 0.2158. Min Act: -0.0003

Data Index: 1435057 (Python Code)

Max Activating Token Index: 895

Text #5

Max Range: 0.2332. Min Range: -0.2332

Max Act: 0.2161. Min Act: -0.0003

Data Index: 1527179 (Python Code)

Max Activating Token Index: 219

Text #6

Max Range: 0.2332. Min Range: -0.2332

Max Act: 0.2020. Min Act: -0.0003

Data Index: 1656010 (Python Code)

Max Activating Token Index: 119

Text #7

Max Range: 0.2332. Min Range: -0.2332

Max Act: 0.2006. Min Act: -0.0003

Data Index: 1380024 (Python Code)

Max Activating Token Index: 523

Text #8

Max Range: 0.2332. Min Range: -0.2332

Max Act: 0.1923. Min Act: -0.0003

Data Index: 1360325 (Python Code)

Max Activating Token Index: 816

Text #9

Max Range: 0.2332. Min Range: -0.2332

Max Act: 0.1908. Min Act: -0.0003

Data Index: 1476764 (Python Code)

Max Activating Token Index: 60

Text #10

Max Range: 0.2332. Min Range: -0.2332

Max Act: 0.1865. Min Act: -0.0003

Data Index: 1422973 (Python Code)

Max Activating Token Index: 658

Text #11

Max Range: 0.2332. Min Range: -0.2332

Max Act: 0.1805. Min Act: -0.0003

Data Index: 1431594 (Python Code)

Max Activating Token Index: 561

Text #12

Max Range: 0.2332. Min Range: -0.2332

Max Act: 0.1825. Min Act: -0.0003

Data Index: 1469802 (Python Code)

Max Activating Token Index: 201

Text #13

Max Range: 0.2332. Min Range: -0.2332

Max Act: 0.1773. Min Act: -0.0003

Data Index: 1631126 (Python Code)

Max Activating Token Index: 892

Text #14

Max Range: 0.2332. Min Range: -0.2332

Max Act: 0.1784. Min Act: -0.0003

Data Index: 1623843 (Python Code)

Max Activating Token Index: 151

Text #15

Max Range: 0.2332. Min Range: -0.2332

Max Act: 0.1834. Min Act: -0.0003

Data Index: 1462552 (Python Code)

Max Activating Token Index: 885

Text #16

Max Range: 0.2332. Min Range: -0.2332

Max Act: 0.1781. Min Act: -0.0003

Data Index: 1621338 (Python Code)

Max Activating Token Index: 485

Text #17

Max Range: 0.2332. Min Range: -0.2332

Max Act: 0.1798. Min Act: -0.0003

Data Index: 1557632 (Python Code)

Max Activating Token Index: 417

Text #18

Max Range: 0.2332. Min Range: -0.2332

Max Act: 0.1820. Min Act: -0.0003

Data Index: 1461677 (Python Code)

Max Activating Token Index: 202

Text #19

Max Range: 0.2332. Min Range: -0.2332

Max Act: 0.1849. Min Act: -0.0003

Data Index: 1582448 (Python Code)

Max Activating Token Index: 309