Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 849 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9558. Min Range: -5.9558
Max Act: 5.9558. Min Act: -0.1700
Data Index: 8803797 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9558. Min Range: -5.9558
Max Act: 5.9558. Min Act: -0.1700
Data Index: 1454555 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9558. Min Range: -5.9558
Max Act: 5.8933. Min Act: -0.1700
Data Index: 4071803 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9558. Min Range: -5.9558
Max Act: 5.8308. Min Act: -0.1700
Data Index: 1265759 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9558. Min Range: -5.9558
Max Act: 5.7996. Min Act: -0.1700
Data Index: 4059206 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9558. Min Range: -5.9558
Max Act: 5.7058. Min Act: -0.1698
Data Index: 3247983 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9558. Min Range: -5.9558
Max Act: 5.7371. Min Act: -0.1700
Data Index: 3006144 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9558. Min Range: -5.9558
Max Act: 5.7058. Min Act: -0.1700
Data Index: 6533908 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9558. Min Range: -5.9558
Max Act: 5.6121. Min Act: -0.1700
Data Index: 7512310 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9558. Min Range: -5.9558
Max Act: 5.6121. Min Act: -0.1700
Data Index: 3507650 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9558. Min Range: -5.9558
Max Act: 5.5183. Min Act: -0.1700
Data Index: 3561389 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9558. Min Range: -5.9558
Max Act: 5.5496. Min Act: -0.1700
Data Index: 8100569 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9558. Min Range: -5.9558
Max Act: 5.5183. Min Act: -0.1700
Data Index: 5375802 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9558. Min Range: -5.9558
Max Act: 5.5496. Min Act: -0.1700
Data Index: 7137778 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9558. Min Range: -5.9558
Max Act: 5.4871. Min Act: -0.1700
Data Index: 7235778 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9558. Min Range: -5.9558
Max Act: 5.4558. Min Act: -0.1700
Data Index: 5789962 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9558. Min Range: -5.9558
Max Act: 5.4246. Min Act: -0.1700
Data Index: 2754910 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9558. Min Range: -5.9558
Max Act: 5.4246. Min Act: -0.1700
Data Index: 7546489 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9558. Min Range: -5.9558
Max Act: 5.4246. Min Act: -0.1700
Data Index: 4173040 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9558. Min Range: -5.9558
Max Act: 5.4558. Min Act: -0.1700
Data Index: 1931520 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #19