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

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

Neuron 2345 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0076. Min Range: -4.0076

Max Act: 4.0076. Min Act: -0.0000

Data Index: 54873 (C4 (Web Text))

Max Activating Token Index: 673

Text #1

Max Range: 4.0076. Min Range: -4.0076

Max Act: 3.7119. Min Act: -0.0000

Data Index: 1048570 (C4 (Web Text))

Max Activating Token Index: 112

Text #2

Max Range: 4.0076. Min Range: -4.0076

Max Act: 3.5348. Min Act: -0.0000

Data Index: 1131285 (C4 (Web Text))

Max Activating Token Index: 238

Text #3

Max Range: 4.0076. Min Range: -4.0076

Max Act: 3.5202. Min Act: -0.0000

Data Index: 1035829 (C4 (Web Text))

Max Activating Token Index: 278

Text #4

Max Range: 4.0076. Min Range: -4.0076

Max Act: 3.2245. Min Act: -0.0000

Data Index: 854514 (C4 (Web Text))

Max Activating Token Index: 110

Text #5

Max Range: 4.0076. Min Range: -4.0076

Max Act: 3.0639. Min Act: -0.0000

Data Index: 263760 (C4 (Web Text))

Max Activating Token Index: 724

Text #6

Max Range: 4.0076. Min Range: -4.0076

Max Act: 3.1670. Min Act: -0.0000

Data Index: 1307137 (C4 (Web Text))

Max Activating Token Index: 198

Text #7

Max Range: 4.0076. Min Range: -4.0076

Max Act: 3.0002. Min Act: -0.0000

Data Index: 885615 (C4 (Web Text))

Max Activating Token Index: 348

Text #8

Max Range: 4.0076. Min Range: -4.0076

Max Act: 3.1353. Min Act: -0.0000

Data Index: 1046672 (C4 (Web Text))

Max Activating Token Index: 970

Text #9

Max Range: 4.0076. Min Range: -4.0076

Max Act: 3.1231. Min Act: -0.0000

Data Index: 1053243 (C4 (Web Text))

Max Activating Token Index: 164

Text #10

Max Range: 4.0076. Min Range: -4.0076

Max Act: 2.8973. Min Act: -0.0000

Data Index: 1344611 (C4 (Web Text))

Max Activating Token Index: 872

Text #11

Max Range: 4.0076. Min Range: -4.0076

Max Act: 3.0495. Min Act: -0.0000

Data Index: 280041 (C4 (Web Text))

Max Activating Token Index: 947

Text #12

Max Range: 4.0076. Min Range: -4.0076

Max Act: 3.0250. Min Act: -0.0000

Data Index: 120787 (C4 (Web Text))

Max Activating Token Index: 765

Text #13

Max Range: 4.0076. Min Range: -4.0076

Max Act: 2.9225. Min Act: -0.0000

Data Index: 426730 (C4 (Web Text))

Max Activating Token Index: 276

Text #14

Max Range: 4.0076. Min Range: -4.0076

Max Act: 3.0343. Min Act: -0.0000

Data Index: 706274 (C4 (Web Text))

Max Activating Token Index: 321

Text #15

Max Range: 4.0076. Min Range: -4.0076

Max Act: 2.7310. Min Act: -0.0000

Data Index: 1200903 (C4 (Web Text))

Max Activating Token Index: 864

Text #16

Max Range: 4.0076. Min Range: -4.0076

Max Act: 2.8780. Min Act: -0.0000

Data Index: 527648 (C4 (Web Text))

Max Activating Token Index: 550

Text #17

Max Range: 4.0076. Min Range: -4.0076

Max Act: 2.8029. Min Act: -0.0000

Data Index: 519028 (C4 (Web Text))

Max Activating Token Index: 46

Text #18

Max Range: 4.0076. Min Range: -4.0076

Max Act: 2.6489. Min Act: -0.0000

Data Index: 221414 (C4 (Web Text))

Max Activating Token Index: 108

Text #19

Max Range: 4.0076. Min Range: -4.0076

Max Act: 2.6340. Min Act: -0.0000

Data Index: 1183916 (C4 (Web Text))

Max Activating Token Index: 859