Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2774 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2002. Min Range: -6.2002
Max Act: 6.2002. Min Act: -0.1700
Data Index: 6288115 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2002. Min Range: -6.2002
Max Act: 6.1690. Min Act: -0.1700
Data Index: 203763 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2002. Min Range: -6.2002
Max Act: 6.1377. Min Act: -0.1700
Data Index: 7187299 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2002. Min Range: -6.2002
Max Act: 6.1377. Min Act: -0.1700
Data Index: 4256856 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2002. Min Range: -6.2002
Max Act: 6.0752. Min Act: -0.1700
Data Index: 1597585 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2002. Min Range: -6.2002
Max Act: 6.0752. Min Act: -0.1700
Data Index: 6097652 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2002. Min Range: -6.2002
Max Act: 6.0752. Min Act: -0.1700
Data Index: 4690409 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2002. Min Range: -6.2002
Max Act: 6.0127. Min Act: -0.1700
Data Index: 2576168 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2002. Min Range: -6.2002
Max Act: 6.0127. Min Act: -0.1700
Data Index: 4613024 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2002. Min Range: -6.2002
Max Act: 6.0440. Min Act: -0.1700
Data Index: 8516527 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2002. Min Range: -6.2002
Max Act: 6.0127. Min Act: -0.1700
Data Index: 6853762 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2002. Min Range: -6.2002
Max Act: 5.9815. Min Act: -0.1700
Data Index: 5881330 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2002. Min Range: -6.2002
Max Act: 5.9815. Min Act: -0.1700
Data Index: 6066969 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2002. Min Range: -6.2002
Max Act: 5.9502. Min Act: -0.1700
Data Index: 8234167 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2002. Min Range: -6.2002
Max Act: 5.9190. Min Act: -0.1700
Data Index: 2764249 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2002. Min Range: -6.2002
Max Act: 5.9502. Min Act: -0.1700
Data Index: 7018958 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2002. Min Range: -6.2002
Max Act: 5.9502. Min Act: -0.1700
Data Index: 6542545 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2002. Min Range: -6.2002
Max Act: 5.9502. Min Act: -0.1700
Data Index: 678365 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2002. Min Range: -6.2002
Max Act: 5.9502. Min Act: -0.1700
Data Index: 8418207 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2002. Min Range: -6.2002
Max Act: 5.9502. Min Act: -0.1700
Data Index: 4341569 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #19