Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5029 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9143. Min Range: -8.9143
Max Act: 8.9143. Min Act: -0.1700
Data Index: 5424927 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9143. Min Range: -8.9143
Max Act: 8.9143. Min Act: -0.1700
Data Index: 3726807 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9143. Min Range: -8.9143
Max Act: 8.7268. Min Act: -0.1700
Data Index: 1433154 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9143. Min Range: -8.9143
Max Act: 8.5393. Min Act: -0.1700
Data Index: 752791 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9143. Min Range: -8.9143
Max Act: 8.5393. Min Act: -0.1700
Data Index: 7251494 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9143. Min Range: -8.9143
Max Act: 8.5393. Min Act: -0.1700
Data Index: 8222193 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9143. Min Range: -8.9143
Max Act: 8.4143. Min Act: -0.1700
Data Index: 5582632 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9143. Min Range: -8.9143
Max Act: 8.2893. Min Act: -0.1700
Data Index: 4462599 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9143. Min Range: -8.9143
Max Act: 8.2268. Min Act: -0.1700
Data Index: 1965469 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9143. Min Range: -8.9143
Max Act: 8.2268. Min Act: -0.1700
Data Index: 7214170 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9143. Min Range: -8.9143
Max Act: 8.2268. Min Act: -0.1700
Data Index: 865619 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9143. Min Range: -8.9143
Max Act: 8.1643. Min Act: -0.1700
Data Index: 3821907 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9143. Min Range: -8.9143
Max Act: 8.1018. Min Act: -0.1700
Data Index: 6341684 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9143. Min Range: -8.9143
Max Act: 8.1018. Min Act: -0.1700
Data Index: 1962750 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9143. Min Range: -8.9143
Max Act: 8.0393. Min Act: -0.1700
Data Index: 2283392 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9143. Min Range: -8.9143
Max Act: 8.0081. Min Act: -0.1700
Data Index: 8356614 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9143. Min Range: -8.9143
Max Act: 8.0393. Min Act: -0.1700
Data Index: 7799692 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9143. Min Range: -8.9143
Max Act: 8.0081. Min Act: -0.1700
Data Index: 4482726 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9143. Min Range: -8.9143
Max Act: 8.0081. Min Act: -0.1700
Data Index: 4426600 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9143. Min Range: -8.9143
Max Act: 7.9456. Min Act: -0.1700
Data Index: 5318570 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #19