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

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

Neuron 2871 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: 0.5253. Min Range: -0.5253

Max Act: 0.4976. Min Act: -0.0002

Data Index: 845339 (C4 (Web Text))

Max Activating Token Index: 673

Text #1

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.5253. Min Act: -0.0002

Data Index: 1108231 (C4 (Web Text))

Max Activating Token Index: 256

Text #2

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.4929. Min Act: -0.0002

Data Index: 1172892 (C4 (Web Text))

Max Activating Token Index: 652

Text #3

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.5090. Min Act: -0.0002

Data Index: 369569 (C4 (Web Text))

Max Activating Token Index: 556

Text #4

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.4872. Min Act: -0.0002

Data Index: 1024777 (C4 (Web Text))

Max Activating Token Index: 712

Text #5

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.4848. Min Act: -0.0002

Data Index: 110497 (C4 (Web Text))

Max Activating Token Index: 488

Text #6

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.4811. Min Act: -0.0002

Data Index: 344224 (C4 (Web Text))

Max Activating Token Index: 278

Text #7

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.4776. Min Act: -0.0002

Data Index: 218761 (C4 (Web Text))

Max Activating Token Index: 540

Text #8

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.4731. Min Act: -0.0002

Data Index: 294339 (C4 (Web Text))

Max Activating Token Index: 219

Text #9

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.4704. Min Act: -0.0002

Data Index: 151636 (C4 (Web Text))

Max Activating Token Index: 755

Text #10

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.4552. Min Act: -0.0002

Data Index: 400147 (C4 (Web Text))

Max Activating Token Index: 115

Text #11

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.4759. Min Act: -0.0002

Data Index: 764010 (C4 (Web Text))

Max Activating Token Index: 944

Text #12

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.4633. Min Act: -0.0002

Data Index: 944978 (C4 (Web Text))

Max Activating Token Index: 791

Text #13

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.4468. Min Act: -0.0002

Data Index: 788126 (C4 (Web Text))

Max Activating Token Index: 662

Text #14

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.4874. Min Act: -0.0002

Data Index: 482028 (C4 (Web Text))

Max Activating Token Index: 365

Text #15

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.4519. Min Act: -0.0002

Data Index: 633952 (C4 (Web Text))

Max Activating Token Index: 371

Text #16

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.4451. Min Act: -0.0002

Data Index: 956367 (C4 (Web Text))

Max Activating Token Index: 161

Text #17

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.4499. Min Act: -0.0002

Data Index: 545290 (C4 (Web Text))

Max Activating Token Index: 529

Text #18

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.4352. Min Act: -0.0002

Data Index: 242867 (C4 (Web Text))

Max Activating Token Index: 655

Text #19

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.4300. Min Act: -0.0002

Data Index: 167117 (C4 (Web Text))

Max Activating Token Index: 76