Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 348 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0958. Min Act: -0.0005

Data Index: 138978 (C4 (Web Text))

Max Activating Token Index: 532

Text #1

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0929. Min Act: -0.0005

Data Index: 1021328 (C4 (Web Text))

Max Activating Token Index: 399

Text #2

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0923. Min Act: -0.0005

Data Index: 1049324 (C4 (Web Text))

Max Activating Token Index: 250

Text #3

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0845. Min Act: -0.0005

Data Index: 673396 (C4 (Web Text))

Max Activating Token Index: 850

Text #4

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0819. Min Act: -0.0005

Data Index: 462750 (C4 (Web Text))

Max Activating Token Index: 368

Text #5

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0824. Min Act: -0.0005

Data Index: 1075011 (C4 (Web Text))

Max Activating Token Index: 203

Text #6

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0803. Min Act: -0.0005

Data Index: 499195 (C4 (Web Text))

Max Activating Token Index: 695

Text #7

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0779. Min Act: -0.0005

Data Index: 1059523 (C4 (Web Text))

Max Activating Token Index: 895

Text #8

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0799. Min Act: -0.0005

Data Index: 604855 (C4 (Web Text))

Max Activating Token Index: 575

Text #9

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0802. Min Act: -0.0005

Data Index: 915954 (C4 (Web Text))

Max Activating Token Index: 885

Text #10

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0770. Min Act: -0.0005

Data Index: 547171 (C4 (Web Text))

Max Activating Token Index: 85

Text #11

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0772. Min Act: -0.0005

Data Index: 375904 (C4 (Web Text))

Max Activating Token Index: 189

Text #12

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0786. Min Act: -0.0005

Data Index: 495525 (C4 (Web Text))

Max Activating Token Index: 188

Text #13

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0800. Min Act: -0.0005

Data Index: 1198013 (C4 (Web Text))

Max Activating Token Index: 68

Text #14

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0781. Min Act: -0.0005

Data Index: 553117 (C4 (Web Text))

Max Activating Token Index: 689

Text #15

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0771. Min Act: -0.0005

Data Index: 50414 (C4 (Web Text))

Max Activating Token Index: 492

Text #16

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0722. Min Act: -0.0005

Data Index: 137266 (C4 (Web Text))

Max Activating Token Index: 367

Text #17

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0726. Min Act: -0.0005

Data Index: 542082 (C4 (Web Text))

Max Activating Token Index: 370

Text #18

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0747. Min Act: -0.0005

Data Index: 1303207 (C4 (Web Text))

Max Activating Token Index: 410

Text #19

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0768. Min Act: -0.0005

Data Index: 241137 (C4 (Web Text))

Max Activating Token Index: 765