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

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

Neuron 3950 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8896. Min Range: -1.8896

Max Act: 1.8896. Min Act: -0.0000

Data Index: 1032806 (C4 (Web Text))

Max Activating Token Index: 344

Text #1

Max Range: 1.8896. Min Range: -1.8896

Max Act: 1.8739. Min Act: -0.0000

Data Index: 772556 (C4 (Web Text))

Max Activating Token Index: 981

Text #2

Max Range: 1.8896. Min Range: -1.8896

Max Act: 1.8151. Min Act: -0.0000

Data Index: 637576 (C4 (Web Text))

Max Activating Token Index: 309

Text #3

Max Range: 1.8896. Min Range: -1.8896

Max Act: 1.6662. Min Act: -0.0000

Data Index: 1136846 (C4 (Web Text))

Max Activating Token Index: 306

Text #4

Max Range: 1.8896. Min Range: -1.8896

Max Act: 1.6593. Min Act: -0.0000

Data Index: 201208 (C4 (Web Text))

Max Activating Token Index: 467

Text #5

Max Range: 1.8896. Min Range: -1.8896

Max Act: 1.6452. Min Act: -0.0000

Data Index: 150981 (C4 (Web Text))

Max Activating Token Index: 999

Text #6

Max Range: 1.8896. Min Range: -1.8896

Max Act: 1.6058. Min Act: -0.0000

Data Index: 652641 (C4 (Web Text))

Max Activating Token Index: 824

Text #7

Max Range: 1.8896. Min Range: -1.8896

Max Act: 1.6127. Min Act: -0.0000

Data Index: 740722 (C4 (Web Text))

Max Activating Token Index: 5

Text #8

Max Range: 1.8896. Min Range: -1.8896

Max Act: 1.4223. Min Act: -0.0000

Data Index: 771880 (C4 (Web Text))

Max Activating Token Index: 644

Text #9

Max Range: 1.8896. Min Range: -1.8896

Max Act: 1.5019. Min Act: -0.0000

Data Index: 405133 (C4 (Web Text))

Max Activating Token Index: 7

Text #10

Max Range: 1.8896. Min Range: -1.8896

Max Act: 1.5346. Min Act: -0.0000

Data Index: 801254 (C4 (Web Text))

Max Activating Token Index: 728

Text #11

Max Range: 1.8896. Min Range: -1.8896

Max Act: 1.5803. Min Act: -0.0000

Data Index: 391120 (C4 (Web Text))

Max Activating Token Index: 847

Text #12

Max Range: 1.8896. Min Range: -1.8896

Max Act: 1.5648. Min Act: -0.0000

Data Index: 864506 (C4 (Web Text))

Max Activating Token Index: 219

Text #13

Max Range: 1.8896. Min Range: -1.8896

Max Act: 1.5199. Min Act: -0.0000

Data Index: 1225902 (C4 (Web Text))

Max Activating Token Index: 936

Text #14

Max Range: 1.8896. Min Range: -1.8896

Max Act: 1.4008. Min Act: -0.0000

Data Index: 807765 (C4 (Web Text))

Max Activating Token Index: 876

Text #15

Max Range: 1.8896. Min Range: -1.8896

Max Act: 1.5098. Min Act: -0.0000

Data Index: 485556 (C4 (Web Text))

Max Activating Token Index: 42

Text #16

Max Range: 1.8896. Min Range: -1.8896

Max Act: 1.4241. Min Act: -0.0000

Data Index: 1481454 (Python Code)

Max Activating Token Index: 295

Text #17

Max Range: 1.8896. Min Range: -1.8896

Max Act: 1.4078. Min Act: -0.0000

Data Index: 797217 (C4 (Web Text))

Max Activating Token Index: 286

Text #18

Max Range: 1.8896. Min Range: -1.8896

Max Act: 1.4090. Min Act: -0.0000

Data Index: 330184 (C4 (Web Text))

Max Activating Token Index: 352

Text #19

Max Range: 1.8896. Min Range: -1.8896

Max Act: 1.3924. Min Act: -0.0000

Data Index: 266239 (C4 (Web Text))

Max Activating Token Index: 416