Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 685 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.2004. Min Range: -0.2004

Max Act: 0.1948. Min Act: -0.0002

Data Index: 1615578 (Python Code)

Max Activating Token Index: 375

Text #1

Max Range: 0.2004. Min Range: -0.2004

Max Act: 0.2004. Min Act: -0.0002

Data Index: 1435876 (Python Code)

Max Activating Token Index: 201

Text #2

Max Range: 0.2004. Min Range: -0.2004

Max Act: 0.1928. Min Act: -0.0002

Data Index: 1490790 (Python Code)

Max Activating Token Index: 171

Text #3

Max Range: 0.2004. Min Range: -0.2004

Max Act: 0.1980. Min Act: -0.0002

Data Index: 1609910 (Python Code)

Max Activating Token Index: 181

Text #4

Max Range: 0.2004. Min Range: -0.2004

Max Act: 0.1935. Min Act: -0.0002

Data Index: 1431641 (Python Code)

Max Activating Token Index: 210

Text #5

Max Range: 0.2004. Min Range: -0.2004

Max Act: 0.1927. Min Act: -0.0002

Data Index: 1567725 (Python Code)

Max Activating Token Index: 198

Text #6

Max Range: 0.2004. Min Range: -0.2004

Max Act: 0.1860. Min Act: -0.0002

Data Index: 1641669 (Python Code)

Max Activating Token Index: 196

Text #7

Max Range: 0.2004. Min Range: -0.2004

Max Act: 0.1902. Min Act: -0.0002

Data Index: 1473785 (Python Code)

Max Activating Token Index: 364

Text #8

Max Range: 0.2004. Min Range: -0.2004

Max Act: 0.1859. Min Act: -0.0002

Data Index: 1617984 (Python Code)

Max Activating Token Index: 853

Text #9

Max Range: 0.2004. Min Range: -0.2004

Max Act: 0.1844. Min Act: -0.0002

Data Index: 1532122 (Python Code)

Max Activating Token Index: 203

Text #10

Max Range: 0.2004. Min Range: -0.2004

Max Act: 0.1808. Min Act: -0.0002

Data Index: 1364300 (Python Code)

Max Activating Token Index: 170

Text #11

Max Range: 0.2004. Min Range: -0.2004

Max Act: 0.1804. Min Act: -0.0002

Data Index: 1602231 (Python Code)

Max Activating Token Index: 328

Text #12

Max Range: 0.2004. Min Range: -0.2004

Max Act: 0.1765. Min Act: -0.0002

Data Index: 1557710 (Python Code)

Max Activating Token Index: 1019

Text #13

Max Range: 0.2004. Min Range: -0.2004

Max Act: 0.1776. Min Act: -0.0002

Data Index: 1645528 (Python Code)

Max Activating Token Index: 96

Text #14

Max Range: 0.2004. Min Range: -0.2004

Max Act: 0.1769. Min Act: -0.0002

Data Index: 1642086 (Python Code)

Max Activating Token Index: 647

Text #15

Max Range: 0.2004. Min Range: -0.2004

Max Act: 0.1771. Min Act: -0.0002

Data Index: 1455246 (Python Code)

Max Activating Token Index: 386

Text #16

Max Range: 0.2004. Min Range: -0.2004

Max Act: 0.1711. Min Act: -0.0002

Data Index: 1381269 (Python Code)

Max Activating Token Index: 409

Text #17

Max Range: 0.2004. Min Range: -0.2004

Max Act: 0.1750. Min Act: -0.0002

Data Index: 1646312 (Python Code)

Max Activating Token Index: 21

Text #18

Max Range: 0.2004. Min Range: -0.2004

Max Act: 0.1672. Min Act: -0.0002

Data Index: 1604593 (Python Code)

Max Activating Token Index: 677

Text #19

Max Range: 0.2004. Min Range: -0.2004

Max Act: 0.1690. Min Act: -0.0002

Data Index: 1379776 (Python Code)

Max Activating Token Index: 717