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

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

Neuron 3888 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.1178. Min Range: -8.1178

Max Act: 8.1178. Min Act: -0.0000

Data Index: 246583 (C4 (Web Text))

Max Activating Token Index: 910

Text #1

Max Range: 8.1178. Min Range: -8.1178

Max Act: 7.7736. Min Act: -0.0000

Data Index: 912085 (C4 (Web Text))

Max Activating Token Index: 265

Text #2

Max Range: 8.1178. Min Range: -8.1178

Max Act: 7.7199. Min Act: -0.0000

Data Index: 523529 (C4 (Web Text))

Max Activating Token Index: 89

Text #3

Max Range: 8.1178. Min Range: -8.1178

Max Act: 6.7767. Min Act: -0.0000

Data Index: 706228 (C4 (Web Text))

Max Activating Token Index: 243

Text #4

Max Range: 8.1178. Min Range: -8.1178

Max Act: 6.8105. Min Act: -0.0000

Data Index: 736348 (C4 (Web Text))

Max Activating Token Index: 355

Text #5

Max Range: 8.1178. Min Range: -8.1178

Max Act: 6.5917. Min Act: -0.0000

Data Index: 1094117 (C4 (Web Text))

Max Activating Token Index: 221

Text #6

Max Range: 8.1178. Min Range: -8.1178

Max Act: 6.5672. Min Act: -0.0000

Data Index: 128256 (C4 (Web Text))

Max Activating Token Index: 126

Text #7

Max Range: 8.1178. Min Range: -8.1178

Max Act: 6.3371. Min Act: -0.0000

Data Index: 1251991 (C4 (Web Text))

Max Activating Token Index: 879

Text #8

Max Range: 8.1178. Min Range: -8.1178

Max Act: 6.6918. Min Act: -0.0000

Data Index: 662069 (C4 (Web Text))

Max Activating Token Index: 1010

Text #9

Max Range: 8.1178. Min Range: -8.1178

Max Act: 6.6261. Min Act: -0.0000

Data Index: 458192 (C4 (Web Text))

Max Activating Token Index: 148

Text #10

Max Range: 8.1178. Min Range: -8.1178

Max Act: 6.8054. Min Act: -0.0000

Data Index: 4482 (C4 (Web Text))

Max Activating Token Index: 683

Text #11

Max Range: 8.1178. Min Range: -8.1178

Max Act: 6.3651. Min Act: -0.0000

Data Index: 1099866 (C4 (Web Text))

Max Activating Token Index: 149

Text #12

Max Range: 8.1178. Min Range: -8.1178

Max Act: 6.3667. Min Act: -0.0000

Data Index: 207595 (C4 (Web Text))

Max Activating Token Index: 885

Text #13

Max Range: 8.1178. Min Range: -8.1178

Max Act: 6.2559. Min Act: -0.0000

Data Index: 36384 (C4 (Web Text))

Max Activating Token Index: 838

Text #14

Max Range: 8.1178. Min Range: -8.1178

Max Act: 5.8215. Min Act: -0.0000

Data Index: 937353 (C4 (Web Text))

Max Activating Token Index: 853

Text #15

Max Range: 8.1178. Min Range: -8.1178

Max Act: 5.2143. Min Act: -0.0000

Data Index: 333452 (C4 (Web Text))

Max Activating Token Index: 231

Text #16

Max Range: 8.1178. Min Range: -8.1178

Max Act: 5.3637. Min Act: -0.0000

Data Index: 361462 (C4 (Web Text))

Max Activating Token Index: 547

Text #17

Max Range: 8.1178. Min Range: -8.1178

Max Act: 5.3176. Min Act: -0.0000

Data Index: 601319 (C4 (Web Text))

Max Activating Token Index: 833

Text #18

Max Range: 8.1178. Min Range: -8.1178

Max Act: 5.7108. Min Act: -0.0000

Data Index: 386995 (C4 (Web Text))

Max Activating Token Index: 618

Text #19

Max Range: 8.1178. Min Range: -8.1178

Max Act: 5.5220. Min Act: -0.0000

Data Index: 779176 (C4 (Web Text))

Max Activating Token Index: 193