Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1067 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4028. Min Range: -8.4028
Max Act: 8.4028. Min Act: -0.1700
Data Index: 7041395 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4028. Min Range: -8.4028
Max Act: 7.5590. Min Act: -0.1700
Data Index: 1588304 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4028. Min Range: -8.4028
Max Act: 7.4965. Min Act: -0.1700
Data Index: 5146905 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4028. Min Range: -8.4028
Max Act: 7.4965. Min Act: -0.1700
Data Index: 1376813 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4028. Min Range: -8.4028
Max Act: 7.4965. Min Act: -0.1700
Data Index: 3568713 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4028. Min Range: -8.4028
Max Act: 7.4965. Min Act: -0.1700
Data Index: 5934435 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4028. Min Range: -8.4028
Max Act: 7.4340. Min Act: -0.1700
Data Index: 4593901 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4028. Min Range: -8.4028
Max Act: 7.4028. Min Act: -0.1700
Data Index: 4244679 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4028. Min Range: -8.4028
Max Act: 7.4028. Min Act: -0.1700
Data Index: 1099177 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4028. Min Range: -8.4028
Max Act: 7.3715. Min Act: -0.1700
Data Index: 7722358 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4028. Min Range: -8.4028
Max Act: 7.4028. Min Act: -0.1700
Data Index: 3473336 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4028. Min Range: -8.4028
Max Act: 7.3403. Min Act: -0.1700
Data Index: 8115806 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4028. Min Range: -8.4028
Max Act: 7.3715. Min Act: -0.1700
Data Index: 8784986 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4028. Min Range: -8.4028
Max Act: 7.2778. Min Act: -0.1700
Data Index: 53588 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4028. Min Range: -8.4028
Max Act: 7.2465. Min Act: -0.1700
Data Index: 1518117 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4028. Min Range: -8.4028
Max Act: 7.2465. Min Act: -0.1700
Data Index: 8333383 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4028. Min Range: -8.4028
Max Act: 7.2153. Min Act: -0.1700
Data Index: 2938092 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4028. Min Range: -8.4028
Max Act: 7.1528. Min Act: -0.1700
Data Index: 4839055 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4028. Min Range: -8.4028
Max Act: 7.1840. Min Act: -0.1700
Data Index: 887086 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4028. Min Range: -8.4028
Max Act: 7.1528. Min Act: -0.1700
Data Index: 4662791 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #19