Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1169 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9939. Min Range: -5.9939
Max Act: 5.9939. Min Act: -0.1700
Data Index: 1258317 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9939. Min Range: -5.9939
Max Act: 5.9002. Min Act: -0.1700
Data Index: 5115098 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9939. Min Range: -5.9939
Max Act: 5.9002. Min Act: -0.1700
Data Index: 3042272 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9939. Min Range: -5.9939
Max Act: 5.8377. Min Act: -0.1694
Data Index: 4527939 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9939. Min Range: -5.9939
Max Act: 5.8377. Min Act: -0.1700
Data Index: 1988590 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9939. Min Range: -5.9939
Max Act: 5.8377. Min Act: -0.1700
Data Index: 7477791 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9939. Min Range: -5.9939
Max Act: 5.8064. Min Act: -0.1700
Data Index: 4965721 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9939. Min Range: -5.9939
Max Act: 5.8064. Min Act: -0.1700
Data Index: 3674707 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9939. Min Range: -5.9939
Max Act: 5.7752. Min Act: -0.1700
Data Index: 7351908 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9939. Min Range: -5.9939
Max Act: 5.8064. Min Act: -0.1700
Data Index: 3034333 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9939. Min Range: -5.9939
Max Act: 5.7752. Min Act: -0.1700
Data Index: 7473771 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9939. Min Range: -5.9939
Max Act: 5.7752. Min Act: -0.1700
Data Index: 5373070 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9939. Min Range: -5.9939
Max Act: 5.7439. Min Act: -0.1700
Data Index: 704713 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9939. Min Range: -5.9939
Max Act: 5.7439. Min Act: -0.1700
Data Index: 6680646 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9939. Min Range: -5.9939
Max Act: 5.7127. Min Act: -0.1700
Data Index: 3318590 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9939. Min Range: -5.9939
Max Act: 5.7127. Min Act: -0.1700
Data Index: 6164264 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9939. Min Range: -5.9939
Max Act: 5.7127. Min Act: -0.1700
Data Index: 7777326 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9939. Min Range: -5.9939
Max Act: 5.7127. Min Act: -0.1700
Data Index: 8120818 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9939. Min Range: -5.9939
Max Act: 5.7127. Min Act: -0.1700
Data Index: 2100007 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9939. Min Range: -5.9939
Max Act: 5.7127. Min Act: -0.1700
Data Index: 2186538 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19