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

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

Neuron 1730 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.4145. Min Range: -6.4145

Max Act: 6.0410. Min Act: -0.0000

Data Index: 912745 (C4 (Web Text))

Max Activating Token Index: 152

Text #1

Max Range: 6.4145. Min Range: -6.4145

Max Act: 6.4145. Min Act: -0.0000

Data Index: 936520 (C4 (Web Text))

Max Activating Token Index: 1019

Text #2

Max Range: 6.4145. Min Range: -6.4145

Max Act: 5.9337. Min Act: -0.0000

Data Index: 913813 (C4 (Web Text))

Max Activating Token Index: 169

Text #3

Max Range: 6.4145. Min Range: -6.4145

Max Act: 5.8875. Min Act: -0.0000

Data Index: 1115249 (C4 (Web Text))

Max Activating Token Index: 191

Text #4

Max Range: 6.4145. Min Range: -6.4145

Max Act: 6.0822. Min Act: -0.0000

Data Index: 214568 (C4 (Web Text))

Max Activating Token Index: 476

Text #5

Max Range: 6.4145. Min Range: -6.4145

Max Act: 6.0827. Min Act: -0.0000

Data Index: 789597 (C4 (Web Text))

Max Activating Token Index: 865

Text #6

Max Range: 6.4145. Min Range: -6.4145

Max Act: 5.4337. Min Act: -0.0000

Data Index: 1244471 (C4 (Web Text))

Max Activating Token Index: 350

Text #7

Max Range: 6.4145. Min Range: -6.4145

Max Act: 4.9840. Min Act: -0.0000

Data Index: 1301473 (C4 (Web Text))

Max Activating Token Index: 878

Text #8

Max Range: 6.4145. Min Range: -6.4145

Max Act: 4.9880. Min Act: -0.0000

Data Index: 575362 (C4 (Web Text))

Max Activating Token Index: 332

Text #9

Max Range: 6.4145. Min Range: -6.4145

Max Act: 5.0760. Min Act: -0.0000

Data Index: 834735 (C4 (Web Text))

Max Activating Token Index: 383

Text #10

Max Range: 6.4145. Min Range: -6.4145

Max Act: 4.5643. Min Act: -0.0000

Data Index: 769585 (C4 (Web Text))

Max Activating Token Index: 308

Text #11

Max Range: 6.4145. Min Range: -6.4145

Max Act: 4.8997. Min Act: -0.0000

Data Index: 955265 (C4 (Web Text))

Max Activating Token Index: 854

Text #12

Max Range: 6.4145. Min Range: -6.4145

Max Act: 4.8315. Min Act: -0.0000

Data Index: 1077732 (C4 (Web Text))

Max Activating Token Index: 915

Text #13

Max Range: 6.4145. Min Range: -6.4145

Max Act: 5.0141. Min Act: -0.0000

Data Index: 520916 (C4 (Web Text))

Max Activating Token Index: 168

Text #14

Max Range: 6.4145. Min Range: -6.4145

Max Act: 4.8078. Min Act: -0.0000

Data Index: 273947 (C4 (Web Text))

Max Activating Token Index: 797

Text #15

Max Range: 6.4145. Min Range: -6.4145

Max Act: 4.6068. Min Act: -0.0000

Data Index: 353333 (C4 (Web Text))

Max Activating Token Index: 483

Text #16

Max Range: 6.4145. Min Range: -6.4145

Max Act: 4.2591. Min Act: -0.0000

Data Index: 256134 (C4 (Web Text))

Max Activating Token Index: 263

Text #17

Max Range: 6.4145. Min Range: -6.4145

Max Act: 4.4195. Min Act: -0.0000

Data Index: 76956 (C4 (Web Text))

Max Activating Token Index: 606

Text #18

Max Range: 6.4145. Min Range: -6.4145

Max Act: 4.7647. Min Act: -0.0000

Data Index: 911241 (C4 (Web Text))

Max Activating Token Index: 125

Text #19

Max Range: 6.4145. Min Range: -6.4145

Max Act: 4.5798. Min Act: -0.0000

Data Index: 1073754 (C4 (Web Text))

Max Activating Token Index: 138