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

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

Neuron 1586 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5237. Min Range: -1.5237

Max Act: 1.5237. Min Act: -0.0001

Data Index: 466156 (C4 (Web Text))

Max Activating Token Index: 520

Text #1

Max Range: 1.5237. Min Range: -1.5237

Max Act: 1.3927. Min Act: -0.0001

Data Index: 770494 (C4 (Web Text))

Max Activating Token Index: 407

Text #2

Max Range: 1.5237. Min Range: -1.5237

Max Act: 1.3340. Min Act: -0.0001

Data Index: 101430 (C4 (Web Text))

Max Activating Token Index: 347

Text #3

Max Range: 1.5237. Min Range: -1.5237

Max Act: 1.1562. Min Act: -0.0001

Data Index: 380297 (C4 (Web Text))

Max Activating Token Index: 908

Text #4

Max Range: 1.5237. Min Range: -1.5237

Max Act: 1.1528. Min Act: -0.0001

Data Index: 489339 (C4 (Web Text))

Max Activating Token Index: 430

Text #5

Max Range: 1.5237. Min Range: -1.5237

Max Act: 1.1535. Min Act: -0.0001

Data Index: 332770 (C4 (Web Text))

Max Activating Token Index: 264

Text #6

Max Range: 1.5237. Min Range: -1.5237

Max Act: 1.1323. Min Act: -0.0001

Data Index: 1209930 (C4 (Web Text))

Max Activating Token Index: 679

Text #7

Max Range: 1.5237. Min Range: -1.5237

Max Act: 1.0799. Min Act: -0.0001

Data Index: 1336373 (C4 (Web Text))

Max Activating Token Index: 679

Text #8

Max Range: 1.5237. Min Range: -1.5237

Max Act: 1.0781. Min Act: -0.0001

Data Index: 125086 (C4 (Web Text))

Max Activating Token Index: 547

Text #9

Max Range: 1.5237. Min Range: -1.5237

Max Act: 1.0281. Min Act: -0.0001

Data Index: 1341809 (C4 (Web Text))

Max Activating Token Index: 908

Text #10

Max Range: 1.5237. Min Range: -1.5237

Max Act: 1.0254. Min Act: -0.0001

Data Index: 47830 (C4 (Web Text))

Max Activating Token Index: 568

Text #11

Max Range: 1.5237. Min Range: -1.5237

Max Act: 0.9602. Min Act: -0.0001

Data Index: 868692 (C4 (Web Text))

Max Activating Token Index: 275

Text #12

Max Range: 1.5237. Min Range: -1.5237

Max Act: 1.0539. Min Act: -0.0001

Data Index: 129128 (C4 (Web Text))

Max Activating Token Index: 928

Text #13

Max Range: 1.5237. Min Range: -1.5237

Max Act: 0.8835. Min Act: -0.0001

Data Index: 1300715 (C4 (Web Text))

Max Activating Token Index: 596

Text #14

Max Range: 1.5237. Min Range: -1.5237

Max Act: 0.9454. Min Act: -0.0001

Data Index: 211383 (C4 (Web Text))

Max Activating Token Index: 694

Text #15

Max Range: 1.5237. Min Range: -1.5237

Max Act: 0.8869. Min Act: -0.0001

Data Index: 1006711 (C4 (Web Text))

Max Activating Token Index: 160

Text #16

Max Range: 1.5237. Min Range: -1.5237

Max Act: 1.0195. Min Act: -0.0001

Data Index: 402197 (C4 (Web Text))

Max Activating Token Index: 855

Text #17

Max Range: 1.5237. Min Range: -1.5237

Max Act: 0.9158. Min Act: -0.0001

Data Index: 673733 (C4 (Web Text))

Max Activating Token Index: 495

Text #18

Max Range: 1.5237. Min Range: -1.5237

Max Act: 0.8483. Min Act: -0.0001

Data Index: 402887 (C4 (Web Text))

Max Activating Token Index: 107

Text #19

Max Range: 1.5237. Min Range: -1.5237

Max Act: 0.8207. Min Act: -0.0001

Data Index: 294997 (C4 (Web Text))

Max Activating Token Index: 351