Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3106 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1085. Min Range: -9.1085
Max Act: 9.1085. Min Act: -0.1700
Data Index: 648456 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1085. Min Range: -9.1085
Max Act: 8.9210. Min Act: -0.1700
Data Index: 1185635 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1085. Min Range: -9.1085
Max Act: 8.7960. Min Act: -0.1700
Data Index: 3045413 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1085. Min Range: -9.1085
Max Act: 8.7335. Min Act: -0.1700
Data Index: 4889942 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1085. Min Range: -9.1085
Max Act: 8.6710. Min Act: -0.1700
Data Index: 1222804 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1085. Min Range: -9.1085
Max Act: 8.6710. Min Act: -0.1700
Data Index: 840681 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1085. Min Range: -9.1085
Max Act: 8.6710. Min Act: -0.1700
Data Index: 5425948 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1085. Min Range: -9.1085
Max Act: 8.6085. Min Act: -0.1700
Data Index: 6852667 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1085. Min Range: -9.1085
Max Act: 8.6085. Min Act: -0.1700
Data Index: 5011831 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1085. Min Range: -9.1085
Max Act: 8.6085. Min Act: -0.1700
Data Index: 4027386 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1085. Min Range: -9.1085
Max Act: 8.6085. Min Act: -0.1700
Data Index: 4322065 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1085. Min Range: -9.1085
Max Act: 8.5460. Min Act: -0.1700
Data Index: 7336705 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1085. Min Range: -9.1085
Max Act: 8.5460. Min Act: -0.1700
Data Index: 1632080 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1085. Min Range: -9.1085
Max Act: 8.5460. Min Act: -0.1700
Data Index: 2747444 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1085. Min Range: -9.1085
Max Act: 8.5460. Min Act: -0.1700
Data Index: 8190512 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1085. Min Range: -9.1085
Max Act: 8.4835. Min Act: -0.1700
Data Index: 3628779 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1085. Min Range: -9.1085
Max Act: 8.4835. Min Act: -0.1700
Data Index: 5355732 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1085. Min Range: -9.1085
Max Act: 8.4835. Min Act: -0.1700
Data Index: 5756037 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1085. Min Range: -9.1085
Max Act: 8.4835. Min Act: -0.1700
Data Index: 8146388 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1085. Min Range: -9.1085
Max Act: 8.4835. Min Act: -0.1700
Data Index: 2909349 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #19