Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3589 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8404. Min Range: -7.8404
Max Act: 7.8404. Min Act: -0.1700
Data Index: 6091288 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8404. Min Range: -7.8404
Max Act: 7.7154. Min Act: -0.1700
Data Index: 1034961 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8404. Min Range: -7.8404
Max Act: 7.4029. Min Act: -0.1700
Data Index: 322111 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8404. Min Range: -7.8404
Max Act: 7.3091. Min Act: -0.1700
Data Index: 8203795 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8404. Min Range: -7.8404
Max Act: 7.1841. Min Act: -0.1700
Data Index: 7932670 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8404. Min Range: -7.8404
Max Act: 7.1529. Min Act: -0.1700
Data Index: 8784971 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8404. Min Range: -7.8404
Max Act: 7.1529. Min Act: -0.1700
Data Index: 241942 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8404. Min Range: -7.8404
Max Act: 7.1216. Min Act: -0.1700
Data Index: 450121 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8404. Min Range: -7.8404
Max Act: 7.0904. Min Act: -0.1700
Data Index: 3571525 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8404. Min Range: -7.8404
Max Act: 7.0904. Min Act: -0.1700
Data Index: 3681555 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8404. Min Range: -7.8404
Max Act: 7.0591. Min Act: -0.1700
Data Index: 7813225 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8404. Min Range: -7.8404
Max Act: 7.0279. Min Act: -0.1700
Data Index: 6149531 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8404. Min Range: -7.8404
Max Act: 6.9966. Min Act: -0.1700
Data Index: 3614313 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8404. Min Range: -7.8404
Max Act: 6.9966. Min Act: -0.1700
Data Index: 423294 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8404. Min Range: -7.8404
Max Act: 6.9654. Min Act: -0.1700
Data Index: 6196528 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8404. Min Range: -7.8404
Max Act: 6.9654. Min Act: -0.1700
Data Index: 7397431 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8404. Min Range: -7.8404
Max Act: 6.9966. Min Act: -0.1700
Data Index: 2560677 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8404. Min Range: -7.8404
Max Act: 6.9341. Min Act: -0.1700
Data Index: 1733187 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8404. Min Range: -7.8404
Max Act: 6.9654. Min Act: -0.1700
Data Index: 3497161 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8404. Min Range: -7.8404
Max Act: 6.9341. Min Act: -0.1700
Data Index: 4253122 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #19