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

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

Neuron 4572 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.1079. Min Act: -0.0001

Data Index: 816879 (C4 (Web Text))

Max Activating Token Index: 478

Text #1

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.1123. Min Act: -0.0001

Data Index: 1018830 (C4 (Web Text))

Max Activating Token Index: 403

Text #2

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.1034. Min Act: -0.0001

Data Index: 799436 (C4 (Web Text))

Max Activating Token Index: 533

Text #3

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.1126. Min Act: -0.0001

Data Index: 932731 (C4 (Web Text))

Max Activating Token Index: 4

Text #4

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0840. Min Act: -0.0001

Data Index: 587021 (C4 (Web Text))

Max Activating Token Index: 214

Text #5

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0942. Min Act: -0.0001

Data Index: 809642 (C4 (Web Text))

Max Activating Token Index: 198

Text #6

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0863. Min Act: -0.0001

Data Index: 878648 (C4 (Web Text))

Max Activating Token Index: 361

Text #7

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0917. Min Act: -0.0001

Data Index: 292111 (C4 (Web Text))

Max Activating Token Index: 636

Text #8

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0890. Min Act: -0.0001

Data Index: 917045 (C4 (Web Text))

Max Activating Token Index: 763

Text #9

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0836. Min Act: -0.0001

Data Index: 201217 (C4 (Web Text))

Max Activating Token Index: 941

Text #10

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0891. Min Act: -0.0001

Data Index: 927133 (C4 (Web Text))

Max Activating Token Index: 454

Text #11

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0792. Min Act: -0.0001

Data Index: 1055801 (C4 (Web Text))

Max Activating Token Index: 10

Text #12

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0814. Min Act: -0.0001

Data Index: 632759 (C4 (Web Text))

Max Activating Token Index: 405

Text #13

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0871. Min Act: -0.0001

Data Index: 245779 (C4 (Web Text))

Max Activating Token Index: 679

Text #14

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0732. Min Act: -0.0001

Data Index: 759975 (C4 (Web Text))

Max Activating Token Index: 906

Text #15

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0724. Min Act: -0.0001

Data Index: 905577 (C4 (Web Text))

Max Activating Token Index: 924

Text #16

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0795. Min Act: -0.0001

Data Index: 1274708 (C4 (Web Text))

Max Activating Token Index: 951

Text #17

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0909. Min Act: -0.0001

Data Index: 184388 (C4 (Web Text))

Max Activating Token Index: 298

Text #18

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0803. Min Act: -0.0001

Data Index: 97206 (C4 (Web Text))

Max Activating Token Index: 243

Text #19

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0765. Min Act: -0.0001

Data Index: 495419 (C4 (Web Text))

Max Activating Token Index: 555