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

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

Neuron 5313 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2908. Min Range: -4.2908

Max Act: 4.2908. Min Act: -0.0000

Data Index: 752996 (C4 (Web Text))

Max Activating Token Index: 132

Text #1

Max Range: 4.2908. Min Range: -4.2908

Max Act: 3.7571. Min Act: -0.0000

Data Index: 5475 (C4 (Web Text))

Max Activating Token Index: 545

Text #2

Max Range: 4.2908. Min Range: -4.2908

Max Act: 3.3785. Min Act: -0.0000

Data Index: 8517 (C4 (Web Text))

Max Activating Token Index: 822

Text #3

Max Range: 4.2908. Min Range: -4.2908

Max Act: 3.3237. Min Act: -0.0000

Data Index: 499773 (C4 (Web Text))

Max Activating Token Index: 257

Text #4

Max Range: 4.2908. Min Range: -4.2908

Max Act: 2.8513. Min Act: -0.0000

Data Index: 25987 (C4 (Web Text))

Max Activating Token Index: 293

Text #5

Max Range: 4.2908. Min Range: -4.2908

Max Act: 2.7006. Min Act: -0.0000

Data Index: 1342684 (C4 (Web Text))

Max Activating Token Index: 259

Text #6

Max Range: 4.2908. Min Range: -4.2908

Max Act: 2.4688. Min Act: -0.0000

Data Index: 403418 (C4 (Web Text))

Max Activating Token Index: 556

Text #7

Max Range: 4.2908. Min Range: -4.2908

Max Act: 1.8666. Min Act: -0.0000

Data Index: 771521 (C4 (Web Text))

Max Activating Token Index: 216

Text #8

Max Range: 4.2908. Min Range: -4.2908

Max Act: 1.8371. Min Act: -0.0000

Data Index: 350439 (C4 (Web Text))

Max Activating Token Index: 42

Text #9

Max Range: 4.2908. Min Range: -4.2908

Max Act: 1.8313. Min Act: -0.0000

Data Index: 1269412 (C4 (Web Text))

Max Activating Token Index: 52

Text #10

Max Range: 4.2908. Min Range: -4.2908

Max Act: 1.8990. Min Act: -0.0000

Data Index: 59831 (C4 (Web Text))

Max Activating Token Index: 231

Text #11

Max Range: 4.2908. Min Range: -4.2908

Max Act: 1.6814. Min Act: -0.0000

Data Index: 356091 (C4 (Web Text))

Max Activating Token Index: 509

Text #12

Max Range: 4.2908. Min Range: -4.2908

Max Act: 1.7596. Min Act: -0.0000

Data Index: 65621 (C4 (Web Text))

Max Activating Token Index: 453

Text #13

Max Range: 4.2908. Min Range: -4.2908

Max Act: 1.6093. Min Act: -0.0000

Data Index: 763178 (C4 (Web Text))

Max Activating Token Index: 493

Text #14

Max Range: 4.2908. Min Range: -4.2908

Max Act: 1.5920. Min Act: -0.0000

Data Index: 1347708 (C4 (Web Text))

Max Activating Token Index: 189

Text #15

Max Range: 4.2908. Min Range: -4.2908

Max Act: 1.5589. Min Act: -0.0000

Data Index: 1226563 (C4 (Web Text))

Max Activating Token Index: 310

Text #16

Max Range: 4.2908. Min Range: -4.2908

Max Act: 1.4676. Min Act: -0.0000

Data Index: 473443 (C4 (Web Text))

Max Activating Token Index: 171

Text #17

Max Range: 4.2908. Min Range: -4.2908

Max Act: 1.4819. Min Act: -0.0000

Data Index: 601682 (C4 (Web Text))

Max Activating Token Index: 209

Text #18

Max Range: 4.2908. Min Range: -4.2908

Max Act: 1.5072. Min Act: -0.0000

Data Index: 1216901 (C4 (Web Text))

Max Activating Token Index: 857

Text #19

Max Range: 4.2908. Min Range: -4.2908

Max Act: 1.4153. Min Act: -0.0000

Data Index: 722383 (C4 (Web Text))

Max Activating Token Index: 777