Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1561 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.4915. Min Range: -1.4915

Max Act: 1.4915. Min Act: -0.0003

Data Index: 899215 (C4 (Web Text))

Max Activating Token Index: 748

Text #1

Max Range: 1.4915. Min Range: -1.4915

Max Act: 1.2030. Min Act: -0.0003

Data Index: 510921 (C4 (Web Text))

Max Activating Token Index: 374

Text #2

Max Range: 1.4915. Min Range: -1.4915

Max Act: 1.2169. Min Act: -0.0003

Data Index: 227246 (C4 (Web Text))

Max Activating Token Index: 156

Text #3

Max Range: 1.4915. Min Range: -1.4915

Max Act: 1.2055. Min Act: -0.0003

Data Index: 1026846 (C4 (Web Text))

Max Activating Token Index: 956

Text #4

Max Range: 1.4915. Min Range: -1.4915

Max Act: 1.1341. Min Act: -0.0003

Data Index: 779285 (C4 (Web Text))

Max Activating Token Index: 464

Text #5

Max Range: 1.4915. Min Range: -1.4915

Max Act: 1.0245. Min Act: -0.0003

Data Index: 717542 (C4 (Web Text))

Max Activating Token Index: 545

Text #6

Max Range: 1.4915. Min Range: -1.4915

Max Act: 1.1697. Min Act: -0.0003

Data Index: 1318639 (C4 (Web Text))

Max Activating Token Index: 579

Text #7

Max Range: 1.4915. Min Range: -1.4915

Max Act: 1.1492. Min Act: -0.0003

Data Index: 757826 (C4 (Web Text))

Max Activating Token Index: 401

Text #8

Max Range: 1.4915. Min Range: -1.4915

Max Act: 1.0921. Min Act: -0.0003

Data Index: 107323 (C4 (Web Text))

Max Activating Token Index: 299

Text #9

Max Range: 1.4915. Min Range: -1.4915

Max Act: 1.1515. Min Act: -0.0003

Data Index: 111952 (C4 (Web Text))

Max Activating Token Index: 166

Text #10

Max Range: 1.4915. Min Range: -1.4915

Max Act: 1.0502. Min Act: -0.0003

Data Index: 593318 (C4 (Web Text))

Max Activating Token Index: 898

Text #11

Max Range: 1.4915. Min Range: -1.4915

Max Act: 1.1247. Min Act: -0.0003

Data Index: 1216334 (C4 (Web Text))

Max Activating Token Index: 739

Text #12

Max Range: 1.4915. Min Range: -1.4915

Max Act: 1.1024. Min Act: -0.0003

Data Index: 635315 (C4 (Web Text))

Max Activating Token Index: 165

Text #13

Max Range: 1.4915. Min Range: -1.4915

Max Act: 1.0090. Min Act: -0.0003

Data Index: 859164 (C4 (Web Text))

Max Activating Token Index: 583

Text #14

Max Range: 1.4915. Min Range: -1.4915

Max Act: 1.1088. Min Act: -0.0003

Data Index: 1267969 (C4 (Web Text))

Max Activating Token Index: 913

Text #15

Max Range: 1.4915. Min Range: -1.4915

Max Act: 0.9555. Min Act: -0.0003

Data Index: 72633 (C4 (Web Text))

Max Activating Token Index: 650

Text #16

Max Range: 1.4915. Min Range: -1.4915

Max Act: 1.0161. Min Act: -0.0003

Data Index: 872695 (C4 (Web Text))

Max Activating Token Index: 33

Text #17

Max Range: 1.4915. Min Range: -1.4915

Max Act: 0.9587. Min Act: -0.0003

Data Index: 928139 (C4 (Web Text))

Max Activating Token Index: 665

Text #18

Max Range: 1.4915. Min Range: -1.4915

Max Act: 1.0458. Min Act: -0.0003

Data Index: 310979 (C4 (Web Text))

Max Activating Token Index: 978

Text #19

Max Range: 1.4915. Min Range: -1.4915

Max Act: 1.0456. Min Act: -0.0003

Data Index: 481116 (C4 (Web Text))

Max Activating Token Index: 132