Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3521 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 0.7564. Min Range: -0.7564
Max Act: 0.7564. Min Act: -0.0001
Data Index: 1176928 (C4 (Web Text))
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.7564. Min Range: -0.7564
Max Act: 0.6836. Min Act: -0.0001
Data Index: 762533 (C4 (Web Text))
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.7564. Min Range: -0.7564
Max Act: 0.6053. Min Act: -0.0001
Data Index: 235416 (C4 (Web Text))
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.7564. Min Range: -0.7564
Max Act: 0.6213. Min Act: -0.0001
Data Index: 181759 (C4 (Web Text))
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.7564. Min Range: -0.7564
Max Act: 0.5621. Min Act: -0.0001
Data Index: 1115125 (C4 (Web Text))
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.7564. Min Range: -0.7564
Max Act: 0.5322. Min Act: -0.0001
Data Index: 1280451 (C4 (Web Text))
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.7564. Min Range: -0.7564
Max Act: 0.5858. Min Act: -0.0001
Data Index: 978809 (C4 (Web Text))
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.7564. Min Range: -0.7564
Max Act: 0.5735. Min Act: -0.0001
Data Index: 14379 (C4 (Web Text))
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.7564. Min Range: -0.7564
Max Act: 0.6141. Min Act: -0.0001
Data Index: 898219 (C4 (Web Text))
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.7564. Min Range: -0.7564
Max Act: 0.5465. Min Act: -0.0001
Data Index: 722942 (C4 (Web Text))
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.7564. Min Range: -0.7564
Max Act: 0.5478. Min Act: -0.0001
Data Index: 1294881 (C4 (Web Text))
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.7564. Min Range: -0.7564
Max Act: 0.5122. Min Act: -0.0001
Data Index: 712703 (C4 (Web Text))
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.7564. Min Range: -0.7564
Max Act: 0.5467. Min Act: -0.0001
Data Index: 907179 (C4 (Web Text))
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.7564. Min Range: -0.7564
Max Act: 0.5447. Min Act: -0.0001
Data Index: 224210 (C4 (Web Text))
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.7564. Min Range: -0.7564
Max Act: 0.5287. Min Act: -0.0001
Data Index: 790423 (C4 (Web Text))
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.7564. Min Range: -0.7564
Max Act: 0.5222. Min Act: -0.0001
Data Index: 1146190 (C4 (Web Text))
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.7564. Min Range: -0.7564
Max Act: 0.5562. Min Act: -0.0001
Data Index: 345788 (C4 (Web Text))
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.7564. Min Range: -0.7564
Max Act: 0.5216. Min Act: -0.0001
Data Index: 1024809 (C4 (Web Text))
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.7564. Min Range: -0.7564
Max Act: 0.4830. Min Act: -0.0001
Data Index: 591319 (C4 (Web Text))
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.7564. Min Range: -0.7564
Max Act: 0.4960. Min Act: -0.0001
Data Index: 45194 (C4 (Web Text))
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #19