Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3482 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7389. Min Range: -6.7389
Max Act: 6.7389. Min Act: -0.1700
Data Index: 1857624 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7389. Min Range: -6.7389
Max Act: 6.7076. Min Act: -0.1700
Data Index: 6880891 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7389. Min Range: -6.7389
Max Act: 6.7076. Min Act: -0.1700
Data Index: 6361163 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7389. Min Range: -6.7389
Max Act: 6.6764. Min Act: -0.1700
Data Index: 1825460 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7389. Min Range: -6.7389
Max Act: 6.6764. Min Act: -0.1700
Data Index: 4799590 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7389. Min Range: -6.7389
Max Act: 6.6451. Min Act: -0.1700
Data Index: 7367557 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7389. Min Range: -6.7389
Max Act: 6.6451. Min Act: -0.1700
Data Index: 5912700 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7389. Min Range: -6.7389
Max Act: 6.6451. Min Act: -0.1700
Data Index: 3020972 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7389. Min Range: -6.7389
Max Act: 6.6451. Min Act: -0.1700
Data Index: 6552171 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7389. Min Range: -6.7389
Max Act: 6.6139. Min Act: -0.1700
Data Index: 4937731 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7389. Min Range: -6.7389
Max Act: 6.6451. Min Act: -0.1700
Data Index: 1819399 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7389. Min Range: -6.7389
Max Act: 6.5514. Min Act: -0.1700
Data Index: 7813094 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7389. Min Range: -6.7389
Max Act: 6.4889. Min Act: -0.1700
Data Index: 687929 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7389. Min Range: -6.7389
Max Act: 6.5201. Min Act: -0.1700
Data Index: 1951302 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7389. Min Range: -6.7389
Max Act: 6.5201. Min Act: -0.1700
Data Index: 2035890 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7389. Min Range: -6.7389
Max Act: 6.5201. Min Act: -0.1700
Data Index: 2409454 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7389. Min Range: -6.7389
Max Act: 6.5201. Min Act: -0.1700
Data Index: 1558426 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7389. Min Range: -6.7389
Max Act: 6.4889. Min Act: -0.1700
Data Index: 4230753 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7389. Min Range: -6.7389
Max Act: 6.4889. Min Act: -0.1700
Data Index: 553804 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7389. Min Range: -6.7389
Max Act: 6.4576. Min Act: -0.1700
Data Index: 2028463 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #19