Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1025 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 6.0502. Min Range: -6.0502
Max Act: 6.0502. Min Act: -0.1700
Data Index: 614709 (C4 (Web Text))
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0502. Min Range: -6.0502
Max Act: 5.9252. Min Act: -0.1700
Data Index: 600476 (C4 (Web Text))
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0502. Min Range: -6.0502
Max Act: 5.9252. Min Act: -0.1700
Data Index: 118196 (C4 (Web Text))
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0502. Min Range: -6.0502
Max Act: 5.9565. Min Act: -0.1699
Data Index: 112674 (C4 (Web Text))
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0502. Min Range: -6.0502
Max Act: 5.8315. Min Act: -0.1700
Data Index: 210204 (C4 (Web Text))
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0502. Min Range: -6.0502
Max Act: 5.8627. Min Act: -0.1700
Data Index: 46169 (C4 (Web Text))
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0502. Min Range: -6.0502
Max Act: 5.8315. Min Act: -0.1700
Data Index: 1123449 (C4 (Web Text))
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0502. Min Range: -6.0502
Max Act: 5.8002. Min Act: -0.1700
Data Index: 1249537 (C4 (Web Text))
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0502. Min Range: -6.0502
Max Act: 5.7065. Min Act: -0.1700
Data Index: 154324 (C4 (Web Text))
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0502. Min Range: -6.0502
Max Act: 5.7065. Min Act: -0.1700
Data Index: 32923 (C4 (Web Text))
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0502. Min Range: -6.0502
Max Act: 5.7377. Min Act: -0.1699
Data Index: 1249057 (C4 (Web Text))
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0502. Min Range: -6.0502
Max Act: 5.6752. Min Act: -0.1700
Data Index: 1103225 (C4 (Web Text))
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0502. Min Range: -6.0502
Max Act: 5.7065. Min Act: -0.1699
Data Index: 1191830 (C4 (Web Text))
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0502. Min Range: -6.0502
Max Act: 5.7377. Min Act: -0.1700
Data Index: 345682 (C4 (Web Text))
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0502. Min Range: -6.0502
Max Act: 5.6752. Min Act: -0.1700
Data Index: 519336 (C4 (Web Text))
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0502. Min Range: -6.0502
Max Act: 5.6752. Min Act: -0.1700
Data Index: 368906 (C4 (Web Text))
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0502. Min Range: -6.0502
Max Act: 5.7065. Min Act: -0.1699
Data Index: 281890 (C4 (Web Text))
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0502. Min Range: -6.0502
Max Act: 5.6440. Min Act: -0.1700
Data Index: 246887 (C4 (Web Text))
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0502. Min Range: -6.0502
Max Act: 5.6752. Min Act: -0.1700
Data Index: 1272838 (C4 (Web Text))
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0502. Min Range: -6.0502
Max Act: 5.6440. Min Act: -0.1700
Data Index: 793216 (C4 (Web Text))
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #19