Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4621 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.0404. Min Range: -7.0404
Max Act: 7.0404. Min Act: -0.1700
Data Index: 4074332 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0404. Min Range: -7.0404
Max Act: 7.0092. Min Act: -0.1700
Data Index: 1184418 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0404. Min Range: -7.0404
Max Act: 6.9779. Min Act: -0.1700
Data Index: 8411010 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0404. Min Range: -7.0404
Max Act: 6.9154. Min Act: -0.1700
Data Index: 6081707 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0404. Min Range: -7.0404
Max Act: 6.8842. Min Act: -0.1700
Data Index: 1849135 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0404. Min Range: -7.0404
Max Act: 6.8529. Min Act: -0.1700
Data Index: 6609089 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0404. Min Range: -7.0404
Max Act: 6.8217. Min Act: -0.1700
Data Index: 2575996 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0404. Min Range: -7.0404
Max Act: 6.8529. Min Act: -0.1700
Data Index: 782639 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0404. Min Range: -7.0404
Max Act: 6.8217. Min Act: -0.1700
Data Index: 8204034 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0404. Min Range: -7.0404
Max Act: 6.7904. Min Act: -0.1700
Data Index: 7017993 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0404. Min Range: -7.0404
Max Act: 6.8217. Min Act: -0.1700
Data Index: 2973717 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0404. Min Range: -7.0404
Max Act: 6.8217. Min Act: -0.1700
Data Index: 2762938 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0404. Min Range: -7.0404
Max Act: 6.8217. Min Act: -0.1700
Data Index: 1921733 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0404. Min Range: -7.0404
Max Act: 6.8217. Min Act: -0.1700
Data Index: 5773546 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0404. Min Range: -7.0404
Max Act: 6.8217. Min Act: -0.1700
Data Index: 6860861 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0404. Min Range: -7.0404
Max Act: 6.7904. Min Act: -0.1700
Data Index: 1304275 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0404. Min Range: -7.0404
Max Act: 6.7592. Min Act: -0.1700
Data Index: 5959084 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0404. Min Range: -7.0404
Max Act: 6.7279. Min Act: -0.1700
Data Index: 1226255 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0404. Min Range: -7.0404
Max Act: 6.7279. Min Act: -0.1700
Data Index: 6956348 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0404. Min Range: -7.0404
Max Act: 6.7279. Min Act: -0.1700
Data Index: 2027760 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #19