Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2084 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9214. Min Range: -0.9214

Max Act: 0.8799. Min Act: -0.0002

Data Index: 481378 (C4 (Web Text))

Max Activating Token Index: 377

Text #1

Max Range: 0.9214. Min Range: -0.9214

Max Act: 0.9214. Min Act: -0.0002

Data Index: 671789 (C4 (Web Text))

Max Activating Token Index: 53

Text #2

Max Range: 0.9214. Min Range: -0.9214

Max Act: 0.7942. Min Act: -0.0002

Data Index: 1347502 (C4 (Web Text))

Max Activating Token Index: 321

Text #3

Max Range: 0.9214. Min Range: -0.9214

Max Act: 0.8407. Min Act: -0.0002

Data Index: 77814 (C4 (Web Text))

Max Activating Token Index: 1001

Text #4

Max Range: 0.9214. Min Range: -0.9214

Max Act: 0.8825. Min Act: -0.0002

Data Index: 1323403 (C4 (Web Text))

Max Activating Token Index: 595

Text #5

Max Range: 0.9214. Min Range: -0.9214

Max Act: 0.8317. Min Act: -0.0002

Data Index: 714646 (C4 (Web Text))

Max Activating Token Index: 313

Text #6

Max Range: 0.9214. Min Range: -0.9214

Max Act: 0.8302. Min Act: -0.0002

Data Index: 551679 (C4 (Web Text))

Max Activating Token Index: 41

Text #7

Max Range: 0.9214. Min Range: -0.9214

Max Act: 0.8258. Min Act: -0.0002

Data Index: 1311000 (C4 (Web Text))

Max Activating Token Index: 709

Text #8

Max Range: 0.9214. Min Range: -0.9214

Max Act: 0.7718. Min Act: -0.0002

Data Index: 149120 (C4 (Web Text))

Max Activating Token Index: 508

Text #9

Max Range: 0.9214. Min Range: -0.9214

Max Act: 0.7897. Min Act: -0.0002

Data Index: 240319 (C4 (Web Text))

Max Activating Token Index: 571

Text #10

Max Range: 0.9214. Min Range: -0.9214

Max Act: 0.7368. Min Act: -0.0002

Data Index: 601013 (C4 (Web Text))

Max Activating Token Index: 727

Text #11

Max Range: 0.9214. Min Range: -0.9214

Max Act: 0.7815. Min Act: -0.0002

Data Index: 166805 (C4 (Web Text))

Max Activating Token Index: 539

Text #12

Max Range: 0.9214. Min Range: -0.9214

Max Act: 0.7367. Min Act: -0.0002

Data Index: 940370 (C4 (Web Text))

Max Activating Token Index: 275

Text #13

Max Range: 0.9214. Min Range: -0.9214

Max Act: 0.7076. Min Act: -0.0002

Data Index: 361666 (C4 (Web Text))

Max Activating Token Index: 640

Text #14

Max Range: 0.9214. Min Range: -0.9214

Max Act: 0.8016. Min Act: -0.0002

Data Index: 57433 (C4 (Web Text))

Max Activating Token Index: 757

Text #15

Max Range: 0.9214. Min Range: -0.9214

Max Act: 0.7167. Min Act: -0.0002

Data Index: 1120634 (C4 (Web Text))

Max Activating Token Index: 978

Text #16

Max Range: 0.9214. Min Range: -0.9214

Max Act: 0.7132. Min Act: -0.0002

Data Index: 684548 (C4 (Web Text))

Max Activating Token Index: 566

Text #17

Max Range: 0.9214. Min Range: -0.9214

Max Act: 0.8156. Min Act: -0.0002

Data Index: 571995 (C4 (Web Text))

Max Activating Token Index: 156

Text #18

Max Range: 0.9214. Min Range: -0.9214

Max Act: 0.7257. Min Act: -0.0002

Data Index: 333397 (C4 (Web Text))

Max Activating Token Index: 990

Text #19

Max Range: 0.9214. Min Range: -0.9214

Max Act: 0.7133. Min Act: -0.0002

Data Index: 214797 (C4 (Web Text))

Max Activating Token Index: 393