Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1280 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.1767. Min Range: -1.1767

Max Act: 1.1666. Min Act: -0.0000

Data Index: 867969 (C4 (Web Text))

Max Activating Token Index: 799

Text #1

Max Range: 1.1767. Min Range: -1.1767

Max Act: 1.1767. Min Act: -0.0000

Data Index: 1214585 (C4 (Web Text))

Max Activating Token Index: 456

Text #2

Max Range: 1.1767. Min Range: -1.1767

Max Act: 1.1085. Min Act: -0.0000

Data Index: 1307859 (C4 (Web Text))

Max Activating Token Index: 93

Text #3

Max Range: 1.1767. Min Range: -1.1767

Max Act: 1.0713. Min Act: -0.0000

Data Index: 1101012 (C4 (Web Text))

Max Activating Token Index: 115

Text #4

Max Range: 1.1767. Min Range: -1.1767

Max Act: 1.1118. Min Act: -0.0000

Data Index: 1198536 (C4 (Web Text))

Max Activating Token Index: 925

Text #5

Max Range: 1.1767. Min Range: -1.1767

Max Act: 1.0494. Min Act: -0.0000

Data Index: 1050543 (C4 (Web Text))

Max Activating Token Index: 64

Text #6

Max Range: 1.1767. Min Range: -1.1767

Max Act: 1.1074. Min Act: -0.0000

Data Index: 731386 (C4 (Web Text))

Max Activating Token Index: 865

Text #7

Max Range: 1.1767. Min Range: -1.1767

Max Act: 1.0269. Min Act: -0.0000

Data Index: 32419 (C4 (Web Text))

Max Activating Token Index: 237

Text #8

Max Range: 1.1767. Min Range: -1.1767

Max Act: 0.9852. Min Act: -0.0000

Data Index: 560863 (C4 (Web Text))

Max Activating Token Index: 802

Text #9

Max Range: 1.1767. Min Range: -1.1767

Max Act: 0.9755. Min Act: -0.0000

Data Index: 1236869 (C4 (Web Text))

Max Activating Token Index: 924

Text #10

Max Range: 1.1767. Min Range: -1.1767

Max Act: 0.9467. Min Act: -0.0000

Data Index: 1223234 (C4 (Web Text))

Max Activating Token Index: 228

Text #11

Max Range: 1.1767. Min Range: -1.1767

Max Act: 0.9127. Min Act: -0.0000

Data Index: 1037310 (C4 (Web Text))

Max Activating Token Index: 238

Text #12

Max Range: 1.1767. Min Range: -1.1767

Max Act: 0.9383. Min Act: -0.0000

Data Index: 1263803 (C4 (Web Text))

Max Activating Token Index: 943

Text #13

Max Range: 1.1767. Min Range: -1.1767

Max Act: 0.9030. Min Act: -0.0000

Data Index: 1023851 (C4 (Web Text))

Max Activating Token Index: 589

Text #14

Max Range: 1.1767. Min Range: -1.1767

Max Act: 0.9080. Min Act: -0.0000

Data Index: 300136 (C4 (Web Text))

Max Activating Token Index: 699

Text #15

Max Range: 1.1767. Min Range: -1.1767

Max Act: 0.9101. Min Act: -0.0000

Data Index: 286395 (C4 (Web Text))

Max Activating Token Index: 58

Text #16

Max Range: 1.1767. Min Range: -1.1767

Max Act: 0.9143. Min Act: -0.0000

Data Index: 153531 (C4 (Web Text))

Max Activating Token Index: 99

Text #17

Max Range: 1.1767. Min Range: -1.1767

Max Act: 1.0112. Min Act: -0.0000

Data Index: 1117033 (C4 (Web Text))

Max Activating Token Index: 850

Text #18

Max Range: 1.1767. Min Range: -1.1767

Max Act: 0.9170. Min Act: -0.0000

Data Index: 1516835 (Python Code)

Max Activating Token Index: 220

Text #19

Max Range: 1.1767. Min Range: -1.1767

Max Act: 0.9338. Min Act: -0.0000

Data Index: 380317 (C4 (Web Text))

Max Activating Token Index: 873