Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4288 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.3074. Min Act: -0.0000

Data Index: 803434 (C4 (Web Text))

Max Activating Token Index: 585

Text #1

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.3052. Min Act: -0.0000

Data Index: 267689 (C4 (Web Text))

Max Activating Token Index: 100

Text #2

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.2633. Min Act: -0.0000

Data Index: 1118124 (C4 (Web Text))

Max Activating Token Index: 407

Text #3

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.2569. Min Act: -0.0000

Data Index: 956662 (C4 (Web Text))

Max Activating Token Index: 299

Text #4

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.2449. Min Act: -0.0000

Data Index: 886006 (C4 (Web Text))

Max Activating Token Index: 808

Text #5

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.2220. Min Act: -0.0000

Data Index: 141173 (C4 (Web Text))

Max Activating Token Index: 928

Text #6

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.2224. Min Act: -0.0000

Data Index: 134924 (C4 (Web Text))

Max Activating Token Index: 588

Text #7

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.2212. Min Act: -0.0000

Data Index: 394670 (C4 (Web Text))

Max Activating Token Index: 272

Text #8

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.2141. Min Act: -0.0000

Data Index: 948646 (C4 (Web Text))

Max Activating Token Index: 460

Text #9

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.2067. Min Act: -0.0000

Data Index: 205296 (C4 (Web Text))

Max Activating Token Index: 895

Text #10

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.2046. Min Act: -0.0000

Data Index: 100515 (C4 (Web Text))

Max Activating Token Index: 545

Text #11

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.1876. Min Act: -0.0000

Data Index: 903179 (C4 (Web Text))

Max Activating Token Index: 424

Text #12

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.2010. Min Act: -0.0000

Data Index: 396093 (C4 (Web Text))

Max Activating Token Index: 901

Text #13

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.1830. Min Act: -0.0000

Data Index: 189194 (C4 (Web Text))

Max Activating Token Index: 828

Text #14

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.1786. Min Act: -0.0000

Data Index: 533687 (C4 (Web Text))

Max Activating Token Index: 301

Text #15

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.1792. Min Act: -0.0000

Data Index: 587473 (C4 (Web Text))

Max Activating Token Index: 878

Text #16

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.1785. Min Act: -0.0000

Data Index: 309140 (C4 (Web Text))

Max Activating Token Index: 623

Text #17

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.1891. Min Act: -0.0000

Data Index: 752343 (C4 (Web Text))

Max Activating Token Index: 182

Text #18

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.1884. Min Act: -0.0000

Data Index: 204109 (C4 (Web Text))

Max Activating Token Index: 118

Text #19

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.1892. Min Act: -0.0000

Data Index: 284837 (C4 (Web Text))

Max Activating Token Index: 152