Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 994 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0976. Min Act: -0.0004

Data Index: 602245 (C4 (Web Text))

Max Activating Token Index: 898

Text #1

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0822. Min Act: -0.0003

Data Index: 1184592 (C4 (Web Text))

Max Activating Token Index: 244

Text #2

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0804. Min Act: -0.0003

Data Index: 1117689 (C4 (Web Text))

Max Activating Token Index: 187

Text #3

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0779. Min Act: -0.0003

Data Index: 247035 (C4 (Web Text))

Max Activating Token Index: 254

Text #4

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0795. Min Act: -0.0003

Data Index: 819444 (C4 (Web Text))

Max Activating Token Index: 286

Text #5

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0781. Min Act: -0.0003

Data Index: 339509 (C4 (Web Text))

Max Activating Token Index: 902

Text #6

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0750. Min Act: -0.0003

Data Index: 997063 (C4 (Web Text))

Max Activating Token Index: 498

Text #7

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0744. Min Act: -0.0003

Data Index: 1186641 (C4 (Web Text))

Max Activating Token Index: 861

Text #8

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0737. Min Act: -0.0003

Data Index: 742288 (C4 (Web Text))

Max Activating Token Index: 382

Text #9

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0745. Min Act: -0.0003

Data Index: 375539 (C4 (Web Text))

Max Activating Token Index: 413

Text #10

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0730. Min Act: -0.0003

Data Index: 1287331 (C4 (Web Text))

Max Activating Token Index: 262

Text #11

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0736. Min Act: -0.0004

Data Index: 613262 (C4 (Web Text))

Max Activating Token Index: 139

Text #12

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0709. Min Act: -0.0003

Data Index: 1019016 (C4 (Web Text))

Max Activating Token Index: 796

Text #13

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0729. Min Act: -0.0003

Data Index: 514036 (C4 (Web Text))

Max Activating Token Index: 428

Text #14

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0722. Min Act: -0.0003

Data Index: 1044231 (C4 (Web Text))

Max Activating Token Index: 1017

Text #15

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0701. Min Act: -0.0003

Data Index: 1162315 (C4 (Web Text))

Max Activating Token Index: 730

Text #16

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0718. Min Act: -0.0004

Data Index: 414588 (C4 (Web Text))

Max Activating Token Index: 242

Text #17

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0721. Min Act: -0.0004

Data Index: 226136 (C4 (Web Text))

Max Activating Token Index: 47

Text #18

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0726. Min Act: -0.0003

Data Index: 97921 (C4 (Web Text))

Max Activating Token Index: 98

Text #19

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0712. Min Act: -0.0003

Data Index: 1141316 (C4 (Web Text))

Max Activating Token Index: 532