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

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

Neuron 2100 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: 0.1642. Min Range: -0.1642

Max Act: 0.1642. Min Act: -0.0000

Data Index: 42498 (C4 (Web Text))

Max Activating Token Index: 984

Text #1

Max Range: 0.1642. Min Range: -0.1642

Max Act: 0.1094. Min Act: -0.0000

Data Index: 533113 (C4 (Web Text))

Max Activating Token Index: 180

Text #2

Max Range: 0.1642. Min Range: -0.1642

Max Act: 0.1139. Min Act: -0.0000

Data Index: 1291196 (C4 (Web Text))

Max Activating Token Index: 83

Text #3

Max Range: 0.1642. Min Range: -0.1642

Max Act: 0.1153. Min Act: -0.0000

Data Index: 552491 (C4 (Web Text))

Max Activating Token Index: 935

Text #4

Max Range: 0.1642. Min Range: -0.1642

Max Act: 0.1174. Min Act: -0.0000

Data Index: 1283874 (C4 (Web Text))

Max Activating Token Index: 309

Text #5

Max Range: 0.1642. Min Range: -0.1642

Max Act: 0.1077. Min Act: -0.0000

Data Index: 516279 (C4 (Web Text))

Max Activating Token Index: 178

Text #6

Max Range: 0.1642. Min Range: -0.1642

Max Act: 0.1066. Min Act: -0.0000

Data Index: 39088 (C4 (Web Text))

Max Activating Token Index: 654

Text #7

Max Range: 0.1642. Min Range: -0.1642

Max Act: 0.1060. Min Act: -0.0000

Data Index: 314180 (C4 (Web Text))

Max Activating Token Index: 1004

Text #8

Max Range: 0.1642. Min Range: -0.1642

Max Act: 0.1011. Min Act: -0.0000

Data Index: 918128 (C4 (Web Text))

Max Activating Token Index: 73

Text #9

Max Range: 0.1642. Min Range: -0.1642

Max Act: 0.0985. Min Act: -0.0000

Data Index: 314936 (C4 (Web Text))

Max Activating Token Index: 163

Text #10

Max Range: 0.1642. Min Range: -0.1642

Max Act: 0.0913. Min Act: -0.0000

Data Index: 130039 (C4 (Web Text))

Max Activating Token Index: 713

Text #11

Max Range: 0.1642. Min Range: -0.1642

Max Act: 0.0907. Min Act: -0.0000

Data Index: 403998 (C4 (Web Text))

Max Activating Token Index: 839

Text #12

Max Range: 0.1642. Min Range: -0.1642

Max Act: 0.0910. Min Act: -0.0000

Data Index: 45441 (C4 (Web Text))

Max Activating Token Index: 699

Text #13

Max Range: 0.1642. Min Range: -0.1642

Max Act: 0.0925. Min Act: -0.0000

Data Index: 13565 (C4 (Web Text))

Max Activating Token Index: 529

Text #14

Max Range: 0.1642. Min Range: -0.1642

Max Act: 0.0895. Min Act: -0.0000

Data Index: 846479 (C4 (Web Text))

Max Activating Token Index: 315

Text #15

Max Range: 0.1642. Min Range: -0.1642

Max Act: 0.0903. Min Act: -0.0000

Data Index: 1136783 (C4 (Web Text))

Max Activating Token Index: 568

Text #16

Max Range: 0.1642. Min Range: -0.1642

Max Act: 0.0873. Min Act: -0.0000

Data Index: 722574 (C4 (Web Text))

Max Activating Token Index: 789

Text #17

Max Range: 0.1642. Min Range: -0.1642

Max Act: 0.0872. Min Act: -0.0000

Data Index: 1137531 (C4 (Web Text))

Max Activating Token Index: 498

Text #18

Max Range: 0.1642. Min Range: -0.1642

Max Act: 0.0822. Min Act: -0.0000

Data Index: 1042973 (C4 (Web Text))

Max Activating Token Index: 650

Text #19

Max Range: 0.1642. Min Range: -0.1642

Max Act: 0.0842. Min Act: -0.0000

Data Index: 1271750 (C4 (Web Text))

Max Activating Token Index: 791