Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 753 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6558. Min Range: -4.6558
Max Act: 4.6558. Min Act: -0.1700
Data Index: 1286310 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6558. Min Range: -4.6558
Max Act: 4.5308. Min Act: -0.1700
Data Index: 7667745 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6558. Min Range: -4.6558
Max Act: 4.4996. Min Act: -0.1700
Data Index: 8819846 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6558. Min Range: -4.6558
Max Act: 4.4996. Min Act: -0.1700
Data Index: 7579144 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6558. Min Range: -4.6558
Max Act: 4.4996. Min Act: -0.1700
Data Index: 6772677 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6558. Min Range: -4.6558
Max Act: 4.4996. Min Act: -0.1700
Data Index: 4078731 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6558. Min Range: -4.6558
Max Act: 4.4996. Min Act: -0.1700
Data Index: 6962956 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6558. Min Range: -4.6558
Max Act: 4.4371. Min Act: -0.1700
Data Index: 1601267 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6558. Min Range: -4.6558
Max Act: 4.4371. Min Act: -0.1700
Data Index: 563265 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6558. Min Range: -4.6558
Max Act: 4.4058. Min Act: -0.1700
Data Index: 3426243 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6558. Min Range: -4.6558
Max Act: 4.4058. Min Act: -0.1700
Data Index: 7397945 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6558. Min Range: -4.6558
Max Act: 4.4058. Min Act: -0.1700
Data Index: 8763843 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6558. Min Range: -4.6558
Max Act: 4.4058. Min Act: -0.1700
Data Index: 4981232 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6558. Min Range: -4.6558
Max Act: 4.3746. Min Act: -0.1700
Data Index: 2926114 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6558. Min Range: -4.6558
Max Act: 4.3746. Min Act: -0.1700
Data Index: 8749878 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6558. Min Range: -4.6558
Max Act: 4.3746. Min Act: -0.1700
Data Index: 2899599 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6558. Min Range: -4.6558
Max Act: 4.3746. Min Act: -0.1700
Data Index: 1798561 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6558. Min Range: -4.6558
Max Act: 4.3433. Min Act: -0.1700
Data Index: 5845251 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6558. Min Range: -4.6558
Max Act: 4.3433. Min Act: -0.1700
Data Index: 6876933 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6558. Min Range: -4.6558
Max Act: 4.3433. Min Act: -0.1700
Data Index: 876889 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #19