Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 72 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1654. Min Range: -5.1654
Max Act: 5.1654. Min Act: -0.1700
Data Index: 7675561 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1654. Min Range: -5.1654
Max Act: 5.0404. Min Act: -0.1700
Data Index: 6478148 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1654. Min Range: -5.1654
Max Act: 5.0404. Min Act: -0.1700
Data Index: 355430 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1654. Min Range: -5.1654
Max Act: 4.9154. Min Act: -0.1700
Data Index: 6888294 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1654. Min Range: -5.1654
Max Act: 4.8529. Min Act: -0.1700
Data Index: 3221890 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1654. Min Range: -5.1654
Max Act: 4.8529. Min Act: -0.1700
Data Index: 560830 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1654. Min Range: -5.1654
Max Act: 4.8217. Min Act: -0.1700
Data Index: 5336762 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1654. Min Range: -5.1654
Max Act: 4.8217. Min Act: -0.1700
Data Index: 7003125 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1654. Min Range: -5.1654
Max Act: 4.7904. Min Act: -0.1700
Data Index: 4293666 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1654. Min Range: -5.1654
Max Act: 4.7904. Min Act: -0.1700
Data Index: 189978 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1654. Min Range: -5.1654
Max Act: 4.7904. Min Act: -0.1700
Data Index: 7946488 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1654. Min Range: -5.1654
Max Act: 4.7592. Min Act: -0.1700
Data Index: 6721868 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1654. Min Range: -5.1654
Max Act: 4.7592. Min Act: -0.1700
Data Index: 2411652 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1654. Min Range: -5.1654
Max Act: 4.7904. Min Act: -0.1700
Data Index: 5684304 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1654. Min Range: -5.1654
Max Act: 4.7279. Min Act: -0.1700
Data Index: 5017783 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1654. Min Range: -5.1654
Max Act: 4.7279. Min Act: -0.1700
Data Index: 4709527 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1654. Min Range: -5.1654
Max Act: 4.7279. Min Act: -0.1700
Data Index: 2755374 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1654. Min Range: -5.1654
Max Act: 4.7279. Min Act: -0.1700
Data Index: 6065855 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1654. Min Range: -5.1654
Max Act: 4.7279. Min Act: -0.1700
Data Index: 1535071 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1654. Min Range: -5.1654
Max Act: 4.7279. Min Act: -0.1700
Data Index: 642190 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #19