Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3532 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7634. Min Range: -7.7634
Max Act: 7.7634. Min Act: -0.1700
Data Index: 7586909 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7634. Min Range: -7.7634
Max Act: 7.6696. Min Act: -0.1700
Data Index: 5490292 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7634. Min Range: -7.7634
Max Act: 7.5759. Min Act: -0.1700
Data Index: 3726432 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7634. Min Range: -7.7634
Max Act: 7.5134. Min Act: -0.1700
Data Index: 7854924 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7634. Min Range: -7.7634
Max Act: 7.4821. Min Act: -0.1700
Data Index: 2151048 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7634. Min Range: -7.7634
Max Act: 7.5134. Min Act: -0.1700
Data Index: 417632 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7634. Min Range: -7.7634
Max Act: 7.2634. Min Act: -0.1700
Data Index: 5009875 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7634. Min Range: -7.7634
Max Act: 7.2009. Min Act: -0.1700
Data Index: 2490814 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7634. Min Range: -7.7634
Max Act: 7.2009. Min Act: -0.1700
Data Index: 1740189 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7634. Min Range: -7.7634
Max Act: 7.2634. Min Act: -0.1700
Data Index: 8635767 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7634. Min Range: -7.7634
Max Act: 7.1696. Min Act: -0.1700
Data Index: 1907906 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7634. Min Range: -7.7634
Max Act: 7.1696. Min Act: -0.1700
Data Index: 7606654 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7634. Min Range: -7.7634
Max Act: 7.1696. Min Act: -0.1700
Data Index: 1315221 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7634. Min Range: -7.7634
Max Act: 7.1696. Min Act: -0.1700
Data Index: 4013256 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7634. Min Range: -7.7634
Max Act: 7.1071. Min Act: -0.1700
Data Index: 4472038 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7634. Min Range: -7.7634
Max Act: 7.1696. Min Act: -0.1700
Data Index: 235768 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7634. Min Range: -7.7634
Max Act: 7.1071. Min Act: -0.1700
Data Index: 6349667 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7634. Min Range: -7.7634
Max Act: 7.0759. Min Act: -0.1700
Data Index: 3549767 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7634. Min Range: -7.7634
Max Act: 7.1071. Min Act: -0.1700
Data Index: 2294787 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7634. Min Range: -7.7634
Max Act: 7.1071. Min Act: -0.1700
Data Index: 5364007 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #19