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

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

Neuron 355 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.8800. Min Range: -6.8800

Max Act: 6.8800. Min Act: -0.0000

Data Index: 1238436 (C4 (Web Text))

Max Activating Token Index: 70

Text #1

Max Range: 6.8800. Min Range: -6.8800

Max Act: 6.6287. Min Act: -0.0000

Data Index: 100044 (C4 (Web Text))

Max Activating Token Index: 48

Text #2

Max Range: 6.8800. Min Range: -6.8800

Max Act: 6.6143. Min Act: -0.0000

Data Index: 243817 (C4 (Web Text))

Max Activating Token Index: 301

Text #3

Max Range: 6.8800. Min Range: -6.8800

Max Act: 6.6056. Min Act: -0.0000

Data Index: 1238154 (C4 (Web Text))

Max Activating Token Index: 86

Text #4

Max Range: 6.8800. Min Range: -6.8800

Max Act: 6.2417. Min Act: -0.0000

Data Index: 22964 (C4 (Web Text))

Max Activating Token Index: 61

Text #5

Max Range: 6.8800. Min Range: -6.8800

Max Act: 5.6325. Min Act: -0.0000

Data Index: 247177 (C4 (Web Text))

Max Activating Token Index: 51

Text #6

Max Range: 6.8800. Min Range: -6.8800

Max Act: 5.8014. Min Act: -0.0000

Data Index: 1106722 (C4 (Web Text))

Max Activating Token Index: 61

Text #7

Max Range: 6.8800. Min Range: -6.8800

Max Act: 5.6193. Min Act: -0.0000

Data Index: 1104429 (C4 (Web Text))

Max Activating Token Index: 749

Text #8

Max Range: 6.8800. Min Range: -6.8800

Max Act: 5.9944. Min Act: -0.0000

Data Index: 1190423 (C4 (Web Text))

Max Activating Token Index: 716

Text #9

Max Range: 6.8800. Min Range: -6.8800

Max Act: 4.6300. Min Act: -0.0000

Data Index: 58322 (C4 (Web Text))

Max Activating Token Index: 816

Text #10

Max Range: 6.8800. Min Range: -6.8800

Max Act: 5.1790. Min Act: -0.0000

Data Index: 92065 (C4 (Web Text))

Max Activating Token Index: 820

Text #11

Max Range: 6.8800. Min Range: -6.8800

Max Act: 5.1316. Min Act: -0.0000

Data Index: 534282 (C4 (Web Text))

Max Activating Token Index: 679

Text #12

Max Range: 6.8800. Min Range: -6.8800

Max Act: 5.0711. Min Act: -0.0000

Data Index: 586993 (C4 (Web Text))

Max Activating Token Index: 688

Text #13

Max Range: 6.8800. Min Range: -6.8800

Max Act: 5.3560. Min Act: -0.0000

Data Index: 1356367 (C4 (Web Text))

Max Activating Token Index: 826

Text #14

Max Range: 6.8800. Min Range: -6.8800

Max Act: 5.1068. Min Act: -0.0000

Data Index: 461255 (C4 (Web Text))

Max Activating Token Index: 204

Text #15

Max Range: 6.8800. Min Range: -6.8800

Max Act: 5.1863. Min Act: -0.0000

Data Index: 1354182 (C4 (Web Text))

Max Activating Token Index: 784

Text #16

Max Range: 6.8800. Min Range: -6.8800

Max Act: 5.1118. Min Act: -0.0000

Data Index: 60675 (C4 (Web Text))

Max Activating Token Index: 43

Text #17

Max Range: 6.8800. Min Range: -6.8800

Max Act: 5.0005. Min Act: -0.0000

Data Index: 355634 (C4 (Web Text))

Max Activating Token Index: 850

Text #18

Max Range: 6.8800. Min Range: -6.8800

Max Act: 4.9693. Min Act: -0.0000

Data Index: 347765 (C4 (Web Text))

Max Activating Token Index: 518

Text #19

Max Range: 6.8800. Min Range: -6.8800

Max Act: 4.9581. Min Act: -0.0000

Data Index: 36012 (C4 (Web Text))

Max Activating Token Index: 479