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

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

Neuron 5744 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.1108. Min Act: -0.0000

Data Index: 442302 (C4 (Web Text))

Max Activating Token Index: 135

Text #1

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.1007. Min Act: -0.0000

Data Index: 946805 (C4 (Web Text))

Max Activating Token Index: 254

Text #2

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.1160. Min Act: -0.0000

Data Index: 1513863 (Python Code)

Max Activating Token Index: 892

Text #3

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.1056. Min Act: -0.0000

Data Index: 136347 (C4 (Web Text))

Max Activating Token Index: 279

Text #4

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.1001. Min Act: -0.0000

Data Index: 14552 (C4 (Web Text))

Max Activating Token Index: 521

Text #5

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0989. Min Act: -0.0000

Data Index: 1186184 (C4 (Web Text))

Max Activating Token Index: 375

Text #6

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0961. Min Act: -0.0000

Data Index: 1060260 (C4 (Web Text))

Max Activating Token Index: 630

Text #7

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0901. Min Act: -0.0000

Data Index: 51017 (C4 (Web Text))

Max Activating Token Index: 996

Text #8

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0962. Min Act: -0.0000

Data Index: 1321394 (C4 (Web Text))

Max Activating Token Index: 143

Text #9

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0884. Min Act: -0.0000

Data Index: 696095 (C4 (Web Text))

Max Activating Token Index: 430

Text #10

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0973. Min Act: -0.0000

Data Index: 302240 (C4 (Web Text))

Max Activating Token Index: 59

Text #11

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0905. Min Act: -0.0000

Data Index: 281953 (C4 (Web Text))

Max Activating Token Index: 673

Text #12

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0879. Min Act: -0.0000

Data Index: 1581112 (Python Code)

Max Activating Token Index: 824

Text #13

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0939. Min Act: -0.0000

Data Index: 606149 (C4 (Web Text))

Max Activating Token Index: 328

Text #14

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0917. Min Act: -0.0000

Data Index: 1065809 (C4 (Web Text))

Max Activating Token Index: 326

Text #15

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0888. Min Act: -0.0000

Data Index: 407574 (C4 (Web Text))

Max Activating Token Index: 87

Text #16

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0742. Min Act: -0.0000

Data Index: 1460145 (Python Code)

Max Activating Token Index: 233

Text #17

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0914. Min Act: -0.0000

Data Index: 541803 (C4 (Web Text))

Max Activating Token Index: 737

Text #18

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0911. Min Act: -0.0000

Data Index: 1287505 (C4 (Web Text))

Max Activating Token Index: 151

Text #19

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0915. Min Act: -0.0000

Data Index: 1647596 (Python Code)

Max Activating Token Index: 679