Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1646 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.1656. Min Act: -0.0000

Data Index: 169104 (C4 (Web Text))

Max Activating Token Index: 761

Text #1

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.1287. Min Act: -0.0000

Data Index: 771122 (C4 (Web Text))

Max Activating Token Index: 18

Text #2

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.1200. Min Act: -0.0000

Data Index: 804599 (C4 (Web Text))

Max Activating Token Index: 446

Text #3

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.1138. Min Act: -0.0000

Data Index: 103948 (C4 (Web Text))

Max Activating Token Index: 52

Text #4

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.1164. Min Act: -0.0000

Data Index: 632208 (C4 (Web Text))

Max Activating Token Index: 921

Text #5

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.1087. Min Act: -0.0000

Data Index: 95945 (C4 (Web Text))

Max Activating Token Index: 197

Text #6

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.1030. Min Act: -0.0000

Data Index: 1292417 (C4 (Web Text))

Max Activating Token Index: 753

Text #7

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.0970. Min Act: -0.0000

Data Index: 128198 (C4 (Web Text))

Max Activating Token Index: 403

Text #8

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.1016. Min Act: -0.0000

Data Index: 167808 (C4 (Web Text))

Max Activating Token Index: 609

Text #9

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.1061. Min Act: -0.0000

Data Index: 141740 (C4 (Web Text))

Max Activating Token Index: 499

Text #10

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.0932. Min Act: -0.0001

Data Index: 586835 (C4 (Web Text))

Max Activating Token Index: 158

Text #11

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.0959. Min Act: -0.0001

Data Index: 1525727 (Python Code)

Max Activating Token Index: 150

Text #12

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.0996. Min Act: -0.0000

Data Index: 1206650 (C4 (Web Text))

Max Activating Token Index: 136

Text #13

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.1060. Min Act: -0.0000

Data Index: 71384 (C4 (Web Text))

Max Activating Token Index: 308

Text #14

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.0943. Min Act: -0.0000

Data Index: 1135116 (C4 (Web Text))

Max Activating Token Index: 888

Text #15

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.0970. Min Act: -0.0000

Data Index: 535767 (C4 (Web Text))

Max Activating Token Index: 332

Text #16

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.0975. Min Act: -0.0000

Data Index: 281377 (C4 (Web Text))

Max Activating Token Index: 166

Text #17

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.0901. Min Act: -0.0000

Data Index: 881547 (C4 (Web Text))

Max Activating Token Index: 972

Text #18

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.0936. Min Act: -0.0001

Data Index: 1120024 (C4 (Web Text))

Max Activating Token Index: 126

Text #19

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.0921. Min Act: -0.0000

Data Index: 659661 (C4 (Web Text))

Max Activating Token Index: 820