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

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

Neuron 3441 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: 0.5120. Min Range: -0.5120

Max Act: 0.5120. Min Act: -0.0002

Data Index: 1178273 (C4 (Web Text))

Max Activating Token Index: 654

Text #1

Max Range: 0.5120. Min Range: -0.5120

Max Act: 0.4194. Min Act: -0.0002

Data Index: 1238227 (C4 (Web Text))

Max Activating Token Index: 833

Text #2

Max Range: 0.5120. Min Range: -0.5120

Max Act: 0.3888. Min Act: -0.0002

Data Index: 272512 (C4 (Web Text))

Max Activating Token Index: 205

Text #3

Max Range: 0.5120. Min Range: -0.5120

Max Act: 0.4032. Min Act: -0.0002

Data Index: 1236518 (C4 (Web Text))

Max Activating Token Index: 303

Text #4

Max Range: 0.5120. Min Range: -0.5120

Max Act: 0.3402. Min Act: -0.0002

Data Index: 348050 (C4 (Web Text))

Max Activating Token Index: 371

Text #5

Max Range: 0.5120. Min Range: -0.5120

Max Act: 0.3500. Min Act: -0.0002

Data Index: 737930 (C4 (Web Text))

Max Activating Token Index: 731

Text #6

Max Range: 0.5120. Min Range: -0.5120

Max Act: 0.3257. Min Act: -0.0002

Data Index: 855699 (C4 (Web Text))

Max Activating Token Index: 139

Text #7

Max Range: 0.5120. Min Range: -0.5120

Max Act: 0.3308. Min Act: -0.0002

Data Index: 505683 (C4 (Web Text))

Max Activating Token Index: 648

Text #8

Max Range: 0.5120. Min Range: -0.5120

Max Act: 0.3522. Min Act: -0.0002

Data Index: 512243 (C4 (Web Text))

Max Activating Token Index: 639

Text #9

Max Range: 0.5120. Min Range: -0.5120

Max Act: 0.3352. Min Act: -0.0002

Data Index: 57054 (C4 (Web Text))

Max Activating Token Index: 419

Text #10

Max Range: 0.5120. Min Range: -0.5120

Max Act: 0.3115. Min Act: -0.0002

Data Index: 652022 (C4 (Web Text))

Max Activating Token Index: 389

Text #11

Max Range: 0.5120. Min Range: -0.5120

Max Act: 0.3260. Min Act: -0.0002

Data Index: 1260066 (C4 (Web Text))

Max Activating Token Index: 651

Text #12

Max Range: 0.5120. Min Range: -0.5120

Max Act: 0.2927. Min Act: -0.0002

Data Index: 176234 (C4 (Web Text))

Max Activating Token Index: 19

Text #13

Max Range: 0.5120. Min Range: -0.5120

Max Act: 0.2704. Min Act: -0.0002

Data Index: 607325 (C4 (Web Text))

Max Activating Token Index: 326

Text #14

Max Range: 0.5120. Min Range: -0.5120

Max Act: 0.2679. Min Act: -0.0002

Data Index: 1171789 (C4 (Web Text))

Max Activating Token Index: 243

Text #15

Max Range: 0.5120. Min Range: -0.5120

Max Act: 0.2902. Min Act: -0.0002

Data Index: 1266352 (C4 (Web Text))

Max Activating Token Index: 760

Text #16

Max Range: 0.5120. Min Range: -0.5120

Max Act: 0.2648. Min Act: -0.0002

Data Index: 54785 (C4 (Web Text))

Max Activating Token Index: 28

Text #17

Max Range: 0.5120. Min Range: -0.5120

Max Act: 0.2642. Min Act: -0.0002

Data Index: 1296049 (C4 (Web Text))

Max Activating Token Index: 908

Text #18

Max Range: 0.5120. Min Range: -0.5120

Max Act: 0.2721. Min Act: -0.0002

Data Index: 447600 (C4 (Web Text))

Max Activating Token Index: 47

Text #19

Max Range: 0.5120. Min Range: -0.5120

Max Act: 0.2409. Min Act: -0.0002

Data Index: 1137731 (C4 (Web Text))

Max Activating Token Index: 1001