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

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

Neuron 3049 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.1281. Min Act: -0.0000

Data Index: 655546 (C4 (Web Text))

Max Activating Token Index: 815

Text #1

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.1207. Min Act: -0.0000

Data Index: 677375 (C4 (Web Text))

Max Activating Token Index: 35

Text #2

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.1223. Min Act: -0.0000

Data Index: 151653 (C4 (Web Text))

Max Activating Token Index: 902

Text #3

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.1111. Min Act: -0.0000

Data Index: 894407 (C4 (Web Text))

Max Activating Token Index: 693

Text #4

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.1091. Min Act: -0.0000

Data Index: 738083 (C4 (Web Text))

Max Activating Token Index: 317

Text #5

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.0944. Min Act: -0.0000

Data Index: 1003436 (C4 (Web Text))

Max Activating Token Index: 814

Text #6

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.0967. Min Act: -0.0000

Data Index: 1340234 (C4 (Web Text))

Max Activating Token Index: 570

Text #7

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.0962. Min Act: -0.0000

Data Index: 385909 (C4 (Web Text))

Max Activating Token Index: 33

Text #8

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.0953. Min Act: -0.0001

Data Index: 507702 (C4 (Web Text))

Max Activating Token Index: 122

Text #9

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.0922. Min Act: -0.0000

Data Index: 636527 (C4 (Web Text))

Max Activating Token Index: 697

Text #10

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.0922. Min Act: -0.0000

Data Index: 1297790 (C4 (Web Text))

Max Activating Token Index: 269

Text #11

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.0912. Min Act: -0.0000

Data Index: 193639 (C4 (Web Text))

Max Activating Token Index: 221

Text #12

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.0942. Min Act: -0.0000

Data Index: 557173 (C4 (Web Text))

Max Activating Token Index: 447

Text #13

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.0939. Min Act: -0.0000

Data Index: 908250 (C4 (Web Text))

Max Activating Token Index: 434

Text #14

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.0922. Min Act: -0.0000

Data Index: 772183 (C4 (Web Text))

Max Activating Token Index: 834

Text #15

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.0911. Min Act: -0.0000

Data Index: 960567 (C4 (Web Text))

Max Activating Token Index: 537

Text #16

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.0950. Min Act: -0.0000

Data Index: 996918 (C4 (Web Text))

Max Activating Token Index: 528

Text #17

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.0920. Min Act: -0.0000

Data Index: 314556 (C4 (Web Text))

Max Activating Token Index: 51

Text #18

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.0918. Min Act: -0.0000

Data Index: 869086 (C4 (Web Text))

Max Activating Token Index: 241

Text #19

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.0886. Min Act: -0.0000

Data Index: 944764 (C4 (Web Text))

Max Activating Token Index: 643