Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1902 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0918. Min Range: -6.0918
Max Act: 6.0918. Min Act: -0.1700
Data Index: 4412143 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0918. Min Range: -6.0918
Max Act: 6.0606. Min Act: -0.1700
Data Index: 5804414 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0918. Min Range: -6.0918
Max Act: 5.9981. Min Act: -0.1700
Data Index: 3574792 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0918. Min Range: -6.0918
Max Act: 5.9981. Min Act: -0.1700
Data Index: 7452481 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0918. Min Range: -6.0918
Max Act: 5.9981. Min Act: -0.1700
Data Index: 7267412 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0918. Min Range: -6.0918
Max Act: 5.9356. Min Act: -0.1700
Data Index: 7355238 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0918. Min Range: -6.0918
Max Act: 5.9668. Min Act: -0.1700
Data Index: 1275642 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0918. Min Range: -6.0918
Max Act: 5.9043. Min Act: -0.1700
Data Index: 2462850 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0918. Min Range: -6.0918
Max Act: 5.9043. Min Act: -0.1700
Data Index: 1209360 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0918. Min Range: -6.0918
Max Act: 5.8731. Min Act: -0.1700
Data Index: 6708616 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0918. Min Range: -6.0918
Max Act: 5.8731. Min Act: -0.1700
Data Index: 434045 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0918. Min Range: -6.0918
Max Act: 5.8731. Min Act: -0.1700
Data Index: 8423282 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0918. Min Range: -6.0918
Max Act: 5.8731. Min Act: -0.1700
Data Index: 5348748 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0918. Min Range: -6.0918
Max Act: 5.8106. Min Act: -0.1700
Data Index: 854438 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0918. Min Range: -6.0918
Max Act: 5.8106. Min Act: -0.1700
Data Index: 5564936 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0918. Min Range: -6.0918
Max Act: 5.7481. Min Act: -0.1700
Data Index: 5492502 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0918. Min Range: -6.0918
Max Act: 5.7793. Min Act: -0.1700
Data Index: 438494 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0918. Min Range: -6.0918
Max Act: 5.7793. Min Act: -0.1700
Data Index: 5459630 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0918. Min Range: -6.0918
Max Act: 5.7168. Min Act: -0.1700
Data Index: 554842 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0918. Min Range: -6.0918
Max Act: 5.7168. Min Act: -0.1700
Data Index: 3964424 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #19