Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2477 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 6.6147. Min Range: -6.6147

Max Act: 6.6147. Min Act: -0.0000

Data Index: 768086 (C4 (Web Text))

Max Activating Token Index: 293

Text #1

Max Range: 6.6147. Min Range: -6.6147

Max Act: 5.8761. Min Act: -0.0000

Data Index: 1239654 (C4 (Web Text))

Max Activating Token Index: 883

Text #2

Max Range: 6.6147. Min Range: -6.6147

Max Act: 5.4151. Min Act: -0.0000

Data Index: 759665 (C4 (Web Text))

Max Activating Token Index: 189

Text #3

Max Range: 6.6147. Min Range: -6.6147

Max Act: 5.0962. Min Act: -0.0000

Data Index: 1096805 (C4 (Web Text))

Max Activating Token Index: 85

Text #4

Max Range: 6.6147. Min Range: -6.6147

Max Act: 5.0411. Min Act: -0.0000

Data Index: 1148932 (C4 (Web Text))

Max Activating Token Index: 1009

Text #5

Max Range: 6.6147. Min Range: -6.6147

Max Act: 4.9370. Min Act: -0.0000

Data Index: 581779 (C4 (Web Text))

Max Activating Token Index: 331

Text #6

Max Range: 6.6147. Min Range: -6.6147

Max Act: 5.0998. Min Act: -0.0000

Data Index: 1212508 (C4 (Web Text))

Max Activating Token Index: 187

Text #7

Max Range: 6.6147. Min Range: -6.6147

Max Act: 5.0483. Min Act: -0.0000

Data Index: 1347 (C4 (Web Text))

Max Activating Token Index: 809

Text #8

Max Range: 6.6147. Min Range: -6.6147

Max Act: 4.7590. Min Act: -0.0000

Data Index: 444456 (C4 (Web Text))

Max Activating Token Index: 612

Text #9

Max Range: 6.6147. Min Range: -6.6147

Max Act: 4.4366. Min Act: -0.0000

Data Index: 1128134 (C4 (Web Text))

Max Activating Token Index: 424

Text #10

Max Range: 6.6147. Min Range: -6.6147

Max Act: 4.7208. Min Act: -0.0000

Data Index: 991814 (C4 (Web Text))

Max Activating Token Index: 152

Text #11

Max Range: 6.6147. Min Range: -6.6147

Max Act: 4.6793. Min Act: -0.0000

Data Index: 86432 (C4 (Web Text))

Max Activating Token Index: 813

Text #12

Max Range: 6.6147. Min Range: -6.6147

Max Act: 4.1197. Min Act: -0.0000

Data Index: 1357759 (C4 (Web Text))

Max Activating Token Index: 292

Text #13

Max Range: 6.6147. Min Range: -6.6147

Max Act: 4.2737. Min Act: -0.0000

Data Index: 697897 (C4 (Web Text))

Max Activating Token Index: 832

Text #14

Max Range: 6.6147. Min Range: -6.6147

Max Act: 4.7266. Min Act: -0.0000

Data Index: 876330 (C4 (Web Text))

Max Activating Token Index: 125

Text #15

Max Range: 6.6147. Min Range: -6.6147

Max Act: 4.3330. Min Act: -0.0000

Data Index: 1112960 (C4 (Web Text))

Max Activating Token Index: 908

Text #16

Max Range: 6.6147. Min Range: -6.6147

Max Act: 4.1501. Min Act: -0.0000

Data Index: 841026 (C4 (Web Text))

Max Activating Token Index: 822

Text #17

Max Range: 6.6147. Min Range: -6.6147

Max Act: 3.6428. Min Act: -0.0000

Data Index: 726185 (C4 (Web Text))

Max Activating Token Index: 934

Text #18

Max Range: 6.6147. Min Range: -6.6147

Max Act: 4.1348. Min Act: -0.0000

Data Index: 694031 (C4 (Web Text))

Max Activating Token Index: 402

Text #19

Max Range: 6.6147. Min Range: -6.6147

Max Act: 4.0723. Min Act: -0.0000

Data Index: 925571 (C4 (Web Text))

Max Activating Token Index: 170