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

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

Neuron 3875 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: 3.6164. Min Range: -3.6164

Max Act: 3.6164. Min Act: -0.0000

Data Index: 390324 (C4 (Web Text))

Max Activating Token Index: 250

Text #1

Max Range: 3.6164. Min Range: -3.6164

Max Act: 3.6048. Min Act: -0.0000

Data Index: 390868 (C4 (Web Text))

Max Activating Token Index: 650

Text #2

Max Range: 3.6164. Min Range: -3.6164

Max Act: 3.5267. Min Act: -0.0000

Data Index: 1166696 (C4 (Web Text))

Max Activating Token Index: 18

Text #3

Max Range: 3.6164. Min Range: -3.6164

Max Act: 2.9235. Min Act: -0.0000

Data Index: 824685 (C4 (Web Text))

Max Activating Token Index: 440

Text #4

Max Range: 3.6164. Min Range: -3.6164

Max Act: 2.5532. Min Act: -0.0000

Data Index: 1124241 (C4 (Web Text))

Max Activating Token Index: 234

Text #5

Max Range: 3.6164. Min Range: -3.6164

Max Act: 2.7568. Min Act: -0.0000

Data Index: 395825 (C4 (Web Text))

Max Activating Token Index: 29

Text #6

Max Range: 3.6164. Min Range: -3.6164

Max Act: 2.6223. Min Act: -0.0000

Data Index: 844536 (C4 (Web Text))

Max Activating Token Index: 119

Text #7

Max Range: 3.6164. Min Range: -3.6164

Max Act: 2.7215. Min Act: -0.0000

Data Index: 481887 (C4 (Web Text))

Max Activating Token Index: 855

Text #8

Max Range: 3.6164. Min Range: -3.6164

Max Act: 2.3705. Min Act: -0.0000

Data Index: 408508 (C4 (Web Text))

Max Activating Token Index: 16

Text #9

Max Range: 3.6164. Min Range: -3.6164

Max Act: 2.4129. Min Act: -0.0000

Data Index: 554415 (C4 (Web Text))

Max Activating Token Index: 174

Text #10

Max Range: 3.6164. Min Range: -3.6164

Max Act: 2.3014. Min Act: -0.0000

Data Index: 531996 (C4 (Web Text))

Max Activating Token Index: 740

Text #11

Max Range: 3.6164. Min Range: -3.6164

Max Act: 2.2446. Min Act: -0.0000

Data Index: 687364 (C4 (Web Text))

Max Activating Token Index: 814

Text #12

Max Range: 3.6164. Min Range: -3.6164

Max Act: 2.3774. Min Act: -0.0000

Data Index: 273746 (C4 (Web Text))

Max Activating Token Index: 568

Text #13

Max Range: 3.6164. Min Range: -3.6164

Max Act: 2.3420. Min Act: -0.0000

Data Index: 46317 (C4 (Web Text))

Max Activating Token Index: 49

Text #14

Max Range: 3.6164. Min Range: -3.6164

Max Act: 2.4452. Min Act: -0.0000

Data Index: 552093 (C4 (Web Text))

Max Activating Token Index: 303

Text #15

Max Range: 3.6164. Min Range: -3.6164

Max Act: 2.1636. Min Act: -0.0000

Data Index: 902124 (C4 (Web Text))

Max Activating Token Index: 744

Text #16

Max Range: 3.6164. Min Range: -3.6164

Max Act: 2.1618. Min Act: -0.0000

Data Index: 521687 (C4 (Web Text))

Max Activating Token Index: 618

Text #17

Max Range: 3.6164. Min Range: -3.6164

Max Act: 2.1362. Min Act: -0.0000

Data Index: 600757 (C4 (Web Text))

Max Activating Token Index: 605

Text #18

Max Range: 3.6164. Min Range: -3.6164

Max Act: 2.1874. Min Act: -0.0000

Data Index: 585050 (C4 (Web Text))

Max Activating Token Index: 578

Text #19

Max Range: 3.6164. Min Range: -3.6164

Max Act: 2.1504. Min Act: -0.0000

Data Index: 886705 (C4 (Web Text))

Max Activating Token Index: 782