Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3470 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8159. Min Range: -8.8159
Max Act: 8.8159. Min Act: -0.1700
Data Index: 7671603 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8159. Min Range: -8.8159
Max Act: 8.1284. Min Act: -0.1700
Data Index: 8550305 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8159. Min Range: -8.8159
Max Act: 8.0659. Min Act: -0.1700
Data Index: 4659445 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8159. Min Range: -8.8159
Max Act: 8.0659. Min Act: -0.1700
Data Index: 6585106 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8159. Min Range: -8.8159
Max Act: 8.0034. Min Act: -0.1700
Data Index: 1490230 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8159. Min Range: -8.8159
Max Act: 7.9721. Min Act: -0.1700
Data Index: 600636 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8159. Min Range: -8.8159
Max Act: 7.9096. Min Act: -0.1700
Data Index: 7582704 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8159. Min Range: -8.8159
Max Act: 7.9096. Min Act: -0.1700
Data Index: 3834085 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8159. Min Range: -8.8159
Max Act: 7.9096. Min Act: -0.1700
Data Index: 4083046 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8159. Min Range: -8.8159
Max Act: 7.8784. Min Act: -0.1700
Data Index: 5105656 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8159. Min Range: -8.8159
Max Act: 7.8784. Min Act: -0.1700
Data Index: 2964156 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8159. Min Range: -8.8159
Max Act: 7.8471. Min Act: -0.1700
Data Index: 8531523 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8159. Min Range: -8.8159
Max Act: 7.8471. Min Act: -0.1700
Data Index: 6595987 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8159. Min Range: -8.8159
Max Act: 7.8471. Min Act: -0.1700
Data Index: 4565903 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8159. Min Range: -8.8159
Max Act: 7.8159. Min Act: -0.1700
Data Index: 8096220 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8159. Min Range: -8.8159
Max Act: 7.8159. Min Act: -0.1700
Data Index: 6733387 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8159. Min Range: -8.8159
Max Act: 7.7846. Min Act: -0.1700
Data Index: 779579 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8159. Min Range: -8.8159
Max Act: 7.7846. Min Act: -0.1700
Data Index: 3249457 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8159. Min Range: -8.8159
Max Act: 7.7846. Min Act: -0.1700
Data Index: 48307 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8159. Min Range: -8.8159
Max Act: 7.7846. Min Act: -0.1700
Data Index: 2954807 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #19