Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1536 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1779. Min Range: -9.1779
Max Act: 9.1779. Min Act: -0.1700
Data Index: 3104919 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1779. Min Range: -9.1779
Max Act: 8.8654. Min Act: -0.1700
Data Index: 1656033 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1779. Min Range: -9.1779
Max Act: 8.6154. Min Act: -0.1700
Data Index: 5604126 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1779. Min Range: -9.1779
Max Act: 8.4904. Min Act: -0.1700
Data Index: 6061930 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1779. Min Range: -9.1779
Max Act: 8.3654. Min Act: -0.1700
Data Index: 3597072 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1779. Min Range: -9.1779
Max Act: 8.3029. Min Act: -0.1700
Data Index: 8665668 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1779. Min Range: -9.1779
Max Act: 8.2404. Min Act: -0.1700
Data Index: 6650683 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1779. Min Range: -9.1779
Max Act: 8.1154. Min Act: -0.1700
Data Index: 1550053 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1779. Min Range: -9.1779
Max Act: 8.1154. Min Act: -0.1700
Data Index: 4201840 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1779. Min Range: -9.1779
Max Act: 8.0529. Min Act: -0.1700
Data Index: 8518796 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1779. Min Range: -9.1779
Max Act: 8.0529. Min Act: -0.1700
Data Index: 4737200 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1779. Min Range: -9.1779
Max Act: 8.0529. Min Act: -0.1700
Data Index: 5877257 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1779. Min Range: -9.1779
Max Act: 8.0529. Min Act: -0.1700
Data Index: 3719259 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1779. Min Range: -9.1779
Max Act: 8.0529. Min Act: -0.1700
Data Index: 7418234 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1779. Min Range: -9.1779
Max Act: 8.0529. Min Act: -0.1700
Data Index: 3963864 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1779. Min Range: -9.1779
Max Act: 7.9904. Min Act: -0.1700
Data Index: 6350519 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1779. Min Range: -9.1779
Max Act: 7.9279. Min Act: -0.1700
Data Index: 2096168 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1779. Min Range: -9.1779
Max Act: 7.9904. Min Act: -0.1700
Data Index: 4834799 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1779. Min Range: -9.1779
Max Act: 7.9904. Min Act: -0.1700
Data Index: 6513309 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1779. Min Range: -9.1779
Max Act: 7.9904. Min Act: -0.1700
Data Index: 7927506 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #19