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

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

Neuron 4829 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1725. Min Range: -3.1725

Max Act: 3.1725. Min Act: -0.0001

Data Index: 414034 (C4 (Web Text))

Max Activating Token Index: 807

Text #1

Max Range: 3.1725. Min Range: -3.1725

Max Act: 3.0731. Min Act: -0.0001

Data Index: 483817 (C4 (Web Text))

Max Activating Token Index: 309

Text #2

Max Range: 3.1725. Min Range: -3.1725

Max Act: 3.0606. Min Act: -0.0001

Data Index: 994481 (C4 (Web Text))

Max Activating Token Index: 999

Text #3

Max Range: 3.1725. Min Range: -3.1725

Max Act: 2.9156. Min Act: -0.0001

Data Index: 99825 (C4 (Web Text))

Max Activating Token Index: 86

Text #4

Max Range: 3.1725. Min Range: -3.1725

Max Act: 2.9483. Min Act: -0.0001

Data Index: 289381 (C4 (Web Text))

Max Activating Token Index: 187

Text #5

Max Range: 3.1725. Min Range: -3.1725

Max Act: 2.9468. Min Act: -0.0001

Data Index: 1046926 (C4 (Web Text))

Max Activating Token Index: 537

Text #6

Max Range: 3.1725. Min Range: -3.1725

Max Act: 2.9195. Min Act: -0.0001

Data Index: 93797 (C4 (Web Text))

Max Activating Token Index: 116

Text #7

Max Range: 3.1725. Min Range: -3.1725

Max Act: 2.7367. Min Act: -0.0001

Data Index: 693605 (C4 (Web Text))

Max Activating Token Index: 803

Text #8

Max Range: 3.1725. Min Range: -3.1725

Max Act: 2.6870. Min Act: -0.0001

Data Index: 1215640 (C4 (Web Text))

Max Activating Token Index: 612

Text #9

Max Range: 3.1725. Min Range: -3.1725

Max Act: 2.9090. Min Act: -0.0001

Data Index: 624616 (C4 (Web Text))

Max Activating Token Index: 397

Text #10

Max Range: 3.1725. Min Range: -3.1725

Max Act: 2.6637. Min Act: -0.0001

Data Index: 829850 (C4 (Web Text))

Max Activating Token Index: 898

Text #11

Max Range: 3.1725. Min Range: -3.1725

Max Act: 2.4915. Min Act: -0.0001

Data Index: 714094 (C4 (Web Text))

Max Activating Token Index: 231

Text #12

Max Range: 3.1725. Min Range: -3.1725

Max Act: 2.4994. Min Act: -0.0001

Data Index: 251617 (C4 (Web Text))

Max Activating Token Index: 600

Text #13

Max Range: 3.1725. Min Range: -3.1725

Max Act: 2.8096. Min Act: -0.0001

Data Index: 842625 (C4 (Web Text))

Max Activating Token Index: 246

Text #14

Max Range: 3.1725. Min Range: -3.1725

Max Act: 2.3243. Min Act: -0.0001

Data Index: 778636 (C4 (Web Text))

Max Activating Token Index: 861

Text #15

Max Range: 3.1725. Min Range: -3.1725

Max Act: 2.6984. Min Act: -0.0001

Data Index: 40017 (C4 (Web Text))

Max Activating Token Index: 137

Text #16

Max Range: 3.1725. Min Range: -3.1725

Max Act: 2.6826. Min Act: -0.0001

Data Index: 1126789 (C4 (Web Text))

Max Activating Token Index: 327

Text #17

Max Range: 3.1725. Min Range: -3.1725

Max Act: 2.6757. Min Act: -0.0001

Data Index: 339227 (C4 (Web Text))

Max Activating Token Index: 561

Text #18

Max Range: 3.1725. Min Range: -3.1725

Max Act: 2.4241. Min Act: -0.0001

Data Index: 302105 (C4 (Web Text))

Max Activating Token Index: 886

Text #19

Max Range: 3.1725. Min Range: -3.1725

Max Act: 2.6616. Min Act: -0.0001

Data Index: 780716 (C4 (Web Text))

Max Activating Token Index: 959