Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4824 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9225. Min Range: -6.9225
Max Act: 6.9225. Min Act: -0.1700
Data Index: 6010047 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9225. Min Range: -6.9225
Max Act: 6.9225. Min Act: -0.1700
Data Index: 894115 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9225. Min Range: -6.9225
Max Act: 6.6412. Min Act: -0.1700
Data Index: 4462254 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9225. Min Range: -6.9225
Max Act: 6.6412. Min Act: -0.1700
Data Index: 7685541 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9225. Min Range: -6.9225
Max Act: 6.6100. Min Act: -0.1700
Data Index: 5765879 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9225. Min Range: -6.9225
Max Act: 6.5787. Min Act: -0.1700
Data Index: 7725706 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9225. Min Range: -6.9225
Max Act: 6.5475. Min Act: -0.1700
Data Index: 5142778 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9225. Min Range: -6.9225
Max Act: 6.5162. Min Act: -0.1700
Data Index: 2088268 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9225. Min Range: -6.9225
Max Act: 6.4850. Min Act: -0.1700
Data Index: 4586933 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9225. Min Range: -6.9225
Max Act: 6.4850. Min Act: -0.1700
Data Index: 3024843 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9225. Min Range: -6.9225
Max Act: 6.4225. Min Act: -0.1700
Data Index: 6599662 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9225. Min Range: -6.9225
Max Act: 6.4225. Min Act: -0.1700
Data Index: 2338106 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9225. Min Range: -6.9225
Max Act: 6.4225. Min Act: -0.1700
Data Index: 5963863 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9225. Min Range: -6.9225
Max Act: 6.3912. Min Act: -0.1700
Data Index: 1355766 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9225. Min Range: -6.9225
Max Act: 6.3912. Min Act: -0.1700
Data Index: 7549965 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9225. Min Range: -6.9225
Max Act: 6.3912. Min Act: -0.1700
Data Index: 3316194 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9225. Min Range: -6.9225
Max Act: 6.3600. Min Act: -0.1700
Data Index: 8137537 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9225. Min Range: -6.9225
Max Act: 6.3600. Min Act: -0.1700
Data Index: 1519620 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9225. Min Range: -6.9225
Max Act: 6.3600. Min Act: -0.1700
Data Index: 5334976 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9225. Min Range: -6.9225
Max Act: 6.3287. Min Act: -0.1700
Data Index: 7725704 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #19