Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2574 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9412. Min Range: -6.9412
Max Act: 6.9412. Min Act: -0.1700
Data Index: 820050 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9412. Min Range: -6.9412
Max Act: 6.9412. Min Act: -0.1700
Data Index: 4522034 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9412. Min Range: -6.9412
Max Act: 6.9412. Min Act: -0.1700
Data Index: 8647151 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9412. Min Range: -6.9412
Max Act: 6.9100. Min Act: -0.1700
Data Index: 2031290 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9412. Min Range: -6.9412
Max Act: 6.8787. Min Act: -0.1700
Data Index: 6554874 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9412. Min Range: -6.9412
Max Act: 6.8475. Min Act: -0.1700
Data Index: 5558101 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9412. Min Range: -6.9412
Max Act: 6.8475. Min Act: -0.1700
Data Index: 4627352 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9412. Min Range: -6.9412
Max Act: 6.8162. Min Act: -0.1700
Data Index: 4011271 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9412. Min Range: -6.9412
Max Act: 6.7537. Min Act: -0.1700
Data Index: 5036030 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9412. Min Range: -6.9412
Max Act: 6.7225. Min Act: -0.1700
Data Index: 3293738 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9412. Min Range: -6.9412
Max Act: 6.7225. Min Act: -0.1700
Data Index: 8830919 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9412. Min Range: -6.9412
Max Act: 6.6600. Min Act: -0.1700
Data Index: 6605481 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9412. Min Range: -6.9412
Max Act: 6.6600. Min Act: -0.1700
Data Index: 3700520 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9412. Min Range: -6.9412
Max Act: 6.6912. Min Act: -0.1700
Data Index: 1780472 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9412. Min Range: -6.9412
Max Act: 6.6600. Min Act: -0.1700
Data Index: 748521 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9412. Min Range: -6.9412
Max Act: 6.6600. Min Act: -0.1700
Data Index: 1864116 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9412. Min Range: -6.9412
Max Act: 6.6287. Min Act: -0.1700
Data Index: 6545809 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9412. Min Range: -6.9412
Max Act: 6.6287. Min Act: -0.1700
Data Index: 1988439 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9412. Min Range: -6.9412
Max Act: 6.5975. Min Act: -0.1700
Data Index: 237554 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9412. Min Range: -6.9412
Max Act: 6.5975. Min Act: -0.1700
Data Index: 7031452 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #19