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

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

Neuron 1990 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: 0.2105. Min Range: -0.2105

Max Act: 0.2105. Min Act: -0.0002

Data Index: 1183385 (C4 (Web Text))

Max Activating Token Index: 331

Text #1

Max Range: 0.2105. Min Range: -0.2105

Max Act: 0.2102. Min Act: -0.0002

Data Index: 269407 (C4 (Web Text))

Max Activating Token Index: 811

Text #2

Max Range: 0.2105. Min Range: -0.2105

Max Act: 0.2021. Min Act: -0.0002

Data Index: 1207358 (C4 (Web Text))

Max Activating Token Index: 970

Text #3

Max Range: 0.2105. Min Range: -0.2105

Max Act: 0.2089. Min Act: -0.0002

Data Index: 915000 (C4 (Web Text))

Max Activating Token Index: 580

Text #4

Max Range: 0.2105. Min Range: -0.2105

Max Act: 0.1974. Min Act: -0.0002

Data Index: 1008531 (C4 (Web Text))

Max Activating Token Index: 345

Text #5

Max Range: 0.2105. Min Range: -0.2105

Max Act: 0.1910. Min Act: -0.0002

Data Index: 1187948 (C4 (Web Text))

Max Activating Token Index: 313

Text #6

Max Range: 0.2105. Min Range: -0.2105

Max Act: 0.1864. Min Act: -0.0002

Data Index: 275498 (C4 (Web Text))

Max Activating Token Index: 816

Text #7

Max Range: 0.2105. Min Range: -0.2105

Max Act: 0.1812. Min Act: -0.0002

Data Index: 435622 (C4 (Web Text))

Max Activating Token Index: 178

Text #8

Max Range: 0.2105. Min Range: -0.2105

Max Act: 0.1838. Min Act: -0.0002

Data Index: 307619 (C4 (Web Text))

Max Activating Token Index: 945

Text #9

Max Range: 0.2105. Min Range: -0.2105

Max Act: 0.1839. Min Act: -0.0002

Data Index: 550956 (C4 (Web Text))

Max Activating Token Index: 378

Text #10

Max Range: 0.2105. Min Range: -0.2105

Max Act: 0.1840. Min Act: -0.0002

Data Index: 443823 (C4 (Web Text))

Max Activating Token Index: 196

Text #11

Max Range: 0.2105. Min Range: -0.2105

Max Act: 0.1828. Min Act: -0.0002

Data Index: 222686 (C4 (Web Text))

Max Activating Token Index: 249

Text #12

Max Range: 0.2105. Min Range: -0.2105

Max Act: 0.1698. Min Act: -0.0002

Data Index: 872484 (C4 (Web Text))

Max Activating Token Index: 153

Text #13

Max Range: 0.2105. Min Range: -0.2105

Max Act: 0.1757. Min Act: -0.0002

Data Index: 337412 (C4 (Web Text))

Max Activating Token Index: 119

Text #14

Max Range: 0.2105. Min Range: -0.2105

Max Act: 0.1740. Min Act: -0.0002

Data Index: 690880 (C4 (Web Text))

Max Activating Token Index: 562

Text #15

Max Range: 0.2105. Min Range: -0.2105

Max Act: 0.1786. Min Act: -0.0002

Data Index: 754311 (C4 (Web Text))

Max Activating Token Index: 571

Text #16

Max Range: 0.2105. Min Range: -0.2105

Max Act: 0.1743. Min Act: -0.0002

Data Index: 336232 (C4 (Web Text))

Max Activating Token Index: 258

Text #17

Max Range: 0.2105. Min Range: -0.2105

Max Act: 0.1711. Min Act: -0.0002

Data Index: 830526 (C4 (Web Text))

Max Activating Token Index: 229

Text #18

Max Range: 0.2105. Min Range: -0.2105

Max Act: 0.1704. Min Act: -0.0002

Data Index: 190339 (C4 (Web Text))

Max Activating Token Index: 77

Text #19

Max Range: 0.2105. Min Range: -0.2105

Max Act: 0.1626. Min Act: -0.0002

Data Index: 1332094 (C4 (Web Text))

Max Activating Token Index: 787