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

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

Neuron 2530 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6118. Min Range: -2.6118

Max Act: 2.6118. Min Act: -0.0000

Data Index: 128791 (C4 (Web Text))

Max Activating Token Index: 629

Text #1

Max Range: 2.6118. Min Range: -2.6118

Max Act: 2.5165. Min Act: -0.0000

Data Index: 1008499 (C4 (Web Text))

Max Activating Token Index: 986

Text #2

Max Range: 2.6118. Min Range: -2.6118

Max Act: 2.2985. Min Act: -0.0000

Data Index: 255595 (C4 (Web Text))

Max Activating Token Index: 562

Text #3

Max Range: 2.6118. Min Range: -2.6118

Max Act: 2.0811. Min Act: -0.0000

Data Index: 1348389 (C4 (Web Text))

Max Activating Token Index: 271

Text #4

Max Range: 2.6118. Min Range: -2.6118

Max Act: 2.0491. Min Act: -0.0000

Data Index: 225890 (C4 (Web Text))

Max Activating Token Index: 256

Text #5

Max Range: 2.6118. Min Range: -2.6118

Max Act: 1.9101. Min Act: -0.0000

Data Index: 197587 (C4 (Web Text))

Max Activating Token Index: 91

Text #6

Max Range: 2.6118. Min Range: -2.6118

Max Act: 1.7984. Min Act: -0.0000

Data Index: 1259857 (C4 (Web Text))

Max Activating Token Index: 983

Text #7

Max Range: 2.6118. Min Range: -2.6118

Max Act: 1.9780. Min Act: -0.0000

Data Index: 2779 (C4 (Web Text))

Max Activating Token Index: 662

Text #8

Max Range: 2.6118. Min Range: -2.6118

Max Act: 1.9274. Min Act: -0.0000

Data Index: 46889 (C4 (Web Text))

Max Activating Token Index: 320

Text #9

Max Range: 2.6118. Min Range: -2.6118

Max Act: 1.7866. Min Act: -0.0000

Data Index: 106980 (C4 (Web Text))

Max Activating Token Index: 217

Text #10

Max Range: 2.6118. Min Range: -2.6118

Max Act: 1.7874. Min Act: -0.0000

Data Index: 448875 (C4 (Web Text))

Max Activating Token Index: 216

Text #11

Max Range: 2.6118. Min Range: -2.6118

Max Act: 1.6438. Min Act: -0.0000

Data Index: 1282193 (C4 (Web Text))

Max Activating Token Index: 191

Text #12

Max Range: 2.6118. Min Range: -2.6118

Max Act: 1.7145. Min Act: -0.0000

Data Index: 415631 (C4 (Web Text))

Max Activating Token Index: 521

Text #13

Max Range: 2.6118. Min Range: -2.6118

Max Act: 1.4984. Min Act: -0.0000

Data Index: 108059 (C4 (Web Text))

Max Activating Token Index: 231

Text #14

Max Range: 2.6118. Min Range: -2.6118

Max Act: 1.4070. Min Act: -0.0000

Data Index: 115332 (C4 (Web Text))

Max Activating Token Index: 750

Text #15

Max Range: 2.6118. Min Range: -2.6118

Max Act: 1.5511. Min Act: -0.0000

Data Index: 285239 (C4 (Web Text))

Max Activating Token Index: 513

Text #16

Max Range: 2.6118. Min Range: -2.6118

Max Act: 1.4954. Min Act: -0.0000

Data Index: 1033492 (C4 (Web Text))

Max Activating Token Index: 836

Text #17

Max Range: 2.6118. Min Range: -2.6118

Max Act: 1.4151. Min Act: -0.0000

Data Index: 178534 (C4 (Web Text))

Max Activating Token Index: 307

Text #18

Max Range: 2.6118. Min Range: -2.6118

Max Act: 1.4991. Min Act: -0.0000

Data Index: 380437 (C4 (Web Text))

Max Activating Token Index: 942

Text #19

Max Range: 2.6118. Min Range: -2.6118

Max Act: 1.4854. Min Act: -0.0000

Data Index: 246251 (C4 (Web Text))

Max Activating Token Index: 580