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

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

Neuron 3654 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4654. Min Range: -0.4654

Max Act: 0.4654. Min Act: -0.0001

Data Index: 896712 (C4 (Web Text))

Max Activating Token Index: 878

Text #1

Max Range: 0.4654. Min Range: -0.4654

Max Act: 0.4077. Min Act: -0.0001

Data Index: 792723 (C4 (Web Text))

Max Activating Token Index: 264

Text #2

Max Range: 0.4654. Min Range: -0.4654

Max Act: 0.4032. Min Act: -0.0001

Data Index: 1144206 (C4 (Web Text))

Max Activating Token Index: 705

Text #3

Max Range: 0.4654. Min Range: -0.4654

Max Act: 0.4125. Min Act: -0.0001

Data Index: 170124 (C4 (Web Text))

Max Activating Token Index: 807

Text #4

Max Range: 0.4654. Min Range: -0.4654

Max Act: 0.3881. Min Act: -0.0001

Data Index: 930502 (C4 (Web Text))

Max Activating Token Index: 389

Text #5

Max Range: 0.4654. Min Range: -0.4654

Max Act: 0.4102. Min Act: -0.0000

Data Index: 53953 (C4 (Web Text))

Max Activating Token Index: 81

Text #6

Max Range: 0.4654. Min Range: -0.4654

Max Act: 0.3847. Min Act: -0.0001

Data Index: 1052324 (C4 (Web Text))

Max Activating Token Index: 749

Text #7

Max Range: 0.4654. Min Range: -0.4654

Max Act: 0.3829. Min Act: -0.0000

Data Index: 68956 (C4 (Web Text))

Max Activating Token Index: 473

Text #8

Max Range: 0.4654. Min Range: -0.4654

Max Act: 0.4099. Min Act: -0.0000

Data Index: 927205 (C4 (Web Text))

Max Activating Token Index: 795

Text #9

Max Range: 0.4654. Min Range: -0.4654

Max Act: 0.4008. Min Act: -0.0001

Data Index: 934836 (C4 (Web Text))

Max Activating Token Index: 598

Text #10

Max Range: 0.4654. Min Range: -0.4654

Max Act: 0.3874. Min Act: -0.0001

Data Index: 218554 (C4 (Web Text))

Max Activating Token Index: 253

Text #11

Max Range: 0.4654. Min Range: -0.4654

Max Act: 0.3906. Min Act: -0.0001

Data Index: 288351 (C4 (Web Text))

Max Activating Token Index: 637

Text #12

Max Range: 0.4654. Min Range: -0.4654

Max Act: 0.3869. Min Act: -0.0001

Data Index: 1269898 (C4 (Web Text))

Max Activating Token Index: 319

Text #13

Max Range: 0.4654. Min Range: -0.4654

Max Act: 0.3926. Min Act: -0.0001

Data Index: 1156372 (C4 (Web Text))

Max Activating Token Index: 171

Text #14

Max Range: 0.4654. Min Range: -0.4654

Max Act: 0.3920. Min Act: -0.0000

Data Index: 1063645 (C4 (Web Text))

Max Activating Token Index: 650

Text #15

Max Range: 0.4654. Min Range: -0.4654

Max Act: 0.3702. Min Act: -0.0001

Data Index: 40094 (C4 (Web Text))

Max Activating Token Index: 536

Text #16

Max Range: 0.4654. Min Range: -0.4654

Max Act: 0.3688. Min Act: -0.0001

Data Index: 298554 (C4 (Web Text))

Max Activating Token Index: 260

Text #17

Max Range: 0.4654. Min Range: -0.4654

Max Act: 0.3764. Min Act: -0.0001

Data Index: 183674 (C4 (Web Text))

Max Activating Token Index: 500

Text #18

Max Range: 0.4654. Min Range: -0.4654

Max Act: 0.3679. Min Act: -0.0001

Data Index: 127864 (C4 (Web Text))

Max Activating Token Index: 460

Text #19

Max Range: 0.4654. Min Range: -0.4654

Max Act: 0.3761. Min Act: -0.0001

Data Index: 1129297 (C4 (Web Text))

Max Activating Token Index: 430