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

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

Neuron 2297 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5799. Min Range: -1.5799

Max Act: 1.5799. Min Act: -0.0002

Data Index: 35016 (C4 (Web Text))

Max Activating Token Index: 221

Text #1

Max Range: 1.5799. Min Range: -1.5799

Max Act: 1.4990. Min Act: -0.0002

Data Index: 407654 (C4 (Web Text))

Max Activating Token Index: 837

Text #2

Max Range: 1.5799. Min Range: -1.5799

Max Act: 1.5098. Min Act: -0.0002

Data Index: 741521 (C4 (Web Text))

Max Activating Token Index: 415

Text #3

Max Range: 1.5799. Min Range: -1.5799

Max Act: 1.4330. Min Act: -0.0002

Data Index: 581372 (C4 (Web Text))

Max Activating Token Index: 777

Text #4

Max Range: 1.5799. Min Range: -1.5799

Max Act: 1.4647. Min Act: -0.0002

Data Index: 312531 (C4 (Web Text))

Max Activating Token Index: 327

Text #5

Max Range: 1.5799. Min Range: -1.5799

Max Act: 1.3095. Min Act: -0.0002

Data Index: 212489 (C4 (Web Text))

Max Activating Token Index: 860

Text #6

Max Range: 1.5799. Min Range: -1.5799

Max Act: 1.2567. Min Act: -0.0002

Data Index: 1172019 (C4 (Web Text))

Max Activating Token Index: 214

Text #7

Max Range: 1.5799. Min Range: -1.5799

Max Act: 1.2236. Min Act: -0.0002

Data Index: 1092706 (C4 (Web Text))

Max Activating Token Index: 326

Text #8

Max Range: 1.5799. Min Range: -1.5799

Max Act: 1.1100. Min Act: -0.0002

Data Index: 556918 (C4 (Web Text))

Max Activating Token Index: 215

Text #9

Max Range: 1.5799. Min Range: -1.5799

Max Act: 1.1722. Min Act: -0.0002

Data Index: 597422 (C4 (Web Text))

Max Activating Token Index: 526

Text #10

Max Range: 1.5799. Min Range: -1.5799

Max Act: 1.1082. Min Act: -0.0002

Data Index: 1009857 (C4 (Web Text))

Max Activating Token Index: 68

Text #11

Max Range: 1.5799. Min Range: -1.5799

Max Act: 1.1001. Min Act: -0.0002

Data Index: 1016910 (C4 (Web Text))

Max Activating Token Index: 793

Text #12

Max Range: 1.5799. Min Range: -1.5799

Max Act: 1.0773. Min Act: -0.0002

Data Index: 1266551 (C4 (Web Text))

Max Activating Token Index: 260

Text #13

Max Range: 1.5799. Min Range: -1.5799

Max Act: 1.0889. Min Act: -0.0002

Data Index: 441268 (C4 (Web Text))

Max Activating Token Index: 365

Text #14

Max Range: 1.5799. Min Range: -1.5799

Max Act: 1.0647. Min Act: -0.0002

Data Index: 3334 (C4 (Web Text))

Max Activating Token Index: 561

Text #15

Max Range: 1.5799. Min Range: -1.5799

Max Act: 1.0751. Min Act: -0.0002

Data Index: 1313937 (C4 (Web Text))

Max Activating Token Index: 850

Text #16

Max Range: 1.5799. Min Range: -1.5799

Max Act: 1.0245. Min Act: -0.0002

Data Index: 187371 (C4 (Web Text))

Max Activating Token Index: 660

Text #17

Max Range: 1.5799. Min Range: -1.5799

Max Act: 1.0133. Min Act: -0.0002

Data Index: 1305589 (C4 (Web Text))

Max Activating Token Index: 561

Text #18

Max Range: 1.5799. Min Range: -1.5799

Max Act: 0.9724. Min Act: -0.0002

Data Index: 1338810 (C4 (Web Text))

Max Activating Token Index: 919

Text #19

Max Range: 1.5799. Min Range: -1.5799

Max Act: 0.9632. Min Act: -0.0002

Data Index: 1264929 (C4 (Web Text))

Max Activating Token Index: 103