Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 971 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 6.0078. Min Range: -6.0078

Max Act: 6.0078. Min Act: -0.0000

Data Index: 939713 (C4 (Web Text))

Max Activating Token Index: 166

Text #1

Max Range: 6.0078. Min Range: -6.0078

Max Act: 4.7466. Min Act: -0.0000

Data Index: 861825 (C4 (Web Text))

Max Activating Token Index: 833

Text #2

Max Range: 6.0078. Min Range: -6.0078

Max Act: 4.4491. Min Act: -0.0000

Data Index: 407800 (C4 (Web Text))

Max Activating Token Index: 412

Text #3

Max Range: 6.0078. Min Range: -6.0078

Max Act: 4.2810. Min Act: -0.0000

Data Index: 979848 (C4 (Web Text))

Max Activating Token Index: 959

Text #4

Max Range: 6.0078. Min Range: -6.0078

Max Act: 4.2672. Min Act: -0.0000

Data Index: 1038013 (C4 (Web Text))

Max Activating Token Index: 733

Text #5

Max Range: 6.0078. Min Range: -6.0078

Max Act: 4.3594. Min Act: -0.0000

Data Index: 936261 (C4 (Web Text))

Max Activating Token Index: 214

Text #6

Max Range: 6.0078. Min Range: -6.0078

Max Act: 4.2906. Min Act: -0.0000

Data Index: 446622 (C4 (Web Text))

Max Activating Token Index: 979

Text #7

Max Range: 6.0078. Min Range: -6.0078

Max Act: 4.0642. Min Act: -0.0000

Data Index: 726355 (C4 (Web Text))

Max Activating Token Index: 112

Text #8

Max Range: 6.0078. Min Range: -6.0078

Max Act: 4.2104. Min Act: -0.0000

Data Index: 908585 (C4 (Web Text))

Max Activating Token Index: 217

Text #9

Max Range: 6.0078. Min Range: -6.0078

Max Act: 4.1794. Min Act: -0.0000

Data Index: 156728 (C4 (Web Text))

Max Activating Token Index: 328

Text #10

Max Range: 6.0078. Min Range: -6.0078

Max Act: 4.0375. Min Act: -0.0000

Data Index: 260191 (C4 (Web Text))

Max Activating Token Index: 945

Text #11

Max Range: 6.0078. Min Range: -6.0078

Max Act: 4.1175. Min Act: -0.0000

Data Index: 1075107 (C4 (Web Text))

Max Activating Token Index: 268

Text #12

Max Range: 6.0078. Min Range: -6.0078

Max Act: 4.1104. Min Act: -0.0000

Data Index: 83079 (C4 (Web Text))

Max Activating Token Index: 593

Text #13

Max Range: 6.0078. Min Range: -6.0078

Max Act: 3.9013. Min Act: -0.0000

Data Index: 1060971 (C4 (Web Text))

Max Activating Token Index: 940

Text #14

Max Range: 6.0078. Min Range: -6.0078

Max Act: 4.0635. Min Act: -0.0000

Data Index: 438967 (C4 (Web Text))

Max Activating Token Index: 353

Text #15

Max Range: 6.0078. Min Range: -6.0078

Max Act: 4.0337. Min Act: -0.0000

Data Index: 163875 (C4 (Web Text))

Max Activating Token Index: 203

Text #16

Max Range: 6.0078. Min Range: -6.0078

Max Act: 4.0227. Min Act: -0.0000

Data Index: 1103898 (C4 (Web Text))

Max Activating Token Index: 361

Text #17

Max Range: 6.0078. Min Range: -6.0078

Max Act: 4.1700. Min Act: -0.0000

Data Index: 408847 (C4 (Web Text))

Max Activating Token Index: 430

Text #18

Max Range: 6.0078. Min Range: -6.0078

Max Act: 4.1484. Min Act: -0.0000

Data Index: 509811 (C4 (Web Text))

Max Activating Token Index: 650

Text #19

Max Range: 6.0078. Min Range: -6.0078

Max Act: 3.8571. Min Act: -0.0000

Data Index: 787022 (C4 (Web Text))

Max Activating Token Index: 968