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

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

Neuron 656 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: 0.1219. Min Range: -0.1219

Max Act: 0.1213. Min Act: -0.0003

Data Index: 1547958 (Python Code)

Max Activating Token Index: 1018

Text #1

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.1219. Min Act: -0.0003

Data Index: 1400882 (Python Code)

Max Activating Token Index: 454

Text #2

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.1195. Min Act: -0.0003

Data Index: 1587893 (Python Code)

Max Activating Token Index: 411

Text #3

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.1139. Min Act: -0.0003

Data Index: 1468555 (Python Code)

Max Activating Token Index: 256

Text #4

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.1073. Min Act: -0.0003

Data Index: 1448312 (Python Code)

Max Activating Token Index: 799

Text #5

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.1046. Min Act: -0.0003

Data Index: 1496735 (Python Code)

Max Activating Token Index: 376

Text #6

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0988. Min Act: -0.0003

Data Index: 1383257 (Python Code)

Max Activating Token Index: 848

Text #7

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0968. Min Act: -0.0003

Data Index: 1615942 (Python Code)

Max Activating Token Index: 193

Text #8

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0925. Min Act: -0.0003

Data Index: 1587877 (Python Code)

Max Activating Token Index: 267

Text #9

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0885. Min Act: -0.0004

Data Index: 1468697 (Python Code)

Max Activating Token Index: 237

Text #10

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0886. Min Act: -0.0003

Data Index: 1647012 (Python Code)

Max Activating Token Index: 966

Text #11

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0890. Min Act: -0.0003

Data Index: 1654691 (Python Code)

Max Activating Token Index: 628

Text #12

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0838. Min Act: -0.0003

Data Index: 1530842 (Python Code)

Max Activating Token Index: 673

Text #13

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0785. Min Act: -0.0003

Data Index: 1482552 (Python Code)

Max Activating Token Index: 180

Text #14

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0846. Min Act: -0.0003

Data Index: 1470514 (Python Code)

Max Activating Token Index: 617

Text #15

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0808. Min Act: -0.0003

Data Index: 1520083 (Python Code)

Max Activating Token Index: 414

Text #16

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0797. Min Act: -0.0003

Data Index: 1569917 (Python Code)

Max Activating Token Index: 472

Text #17

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0785. Min Act: -0.0003

Data Index: 1493428 (Python Code)

Max Activating Token Index: 295

Text #18

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0811. Min Act: -0.0003

Data Index: 1570832 (Python Code)

Max Activating Token Index: 919

Text #19

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0770. Min Act: -0.0003

Data Index: 1447983 (Python Code)

Max Activating Token Index: 664