Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3283 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.7222. Min Range: -10.7222
Max Act: 10.7222. Min Act: -0.1700
Data Index: 1547635 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.7222. Min Range: -10.7222
Max Act: 10.2222. Min Act: -0.1700
Data Index: 8128729 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.7222. Min Range: -10.7222
Max Act: 9.9097. Min Act: -0.1700
Data Index: 6492372 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.7222. Min Range: -10.7222
Max Act: 9.9097. Min Act: -0.1700
Data Index: 8436622 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.7222. Min Range: -10.7222
Max Act: 9.8472. Min Act: -0.1700
Data Index: 5229768 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.7222. Min Range: -10.7222
Max Act: 9.7847. Min Act: -0.1700
Data Index: 1832803 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.7222. Min Range: -10.7222
Max Act: 9.7847. Min Act: -0.1700
Data Index: 4661645 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.7222. Min Range: -10.7222
Max Act: 9.7222. Min Act: -0.1700
Data Index: 1149862 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.7222. Min Range: -10.7222
Max Act: 9.7222. Min Act: -0.1700
Data Index: 3502501 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.7222. Min Range: -10.7222
Max Act: 9.7222. Min Act: -0.1700
Data Index: 1038937 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.7222. Min Range: -10.7222
Max Act: 9.7222. Min Act: -0.1700
Data Index: 8661400 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.7222. Min Range: -10.7222
Max Act: 9.7222. Min Act: -0.1700
Data Index: 6684429 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.7222. Min Range: -10.7222
Max Act: 9.6597. Min Act: -0.1700
Data Index: 5713005 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.7222. Min Range: -10.7222
Max Act: 9.6597. Min Act: -0.1700
Data Index: 6071195 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.7222. Min Range: -10.7222
Max Act: 9.6597. Min Act: -0.1700
Data Index: 7340156 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.7222. Min Range: -10.7222
Max Act: 9.5972. Min Act: -0.1700
Data Index: 8355724 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.7222. Min Range: -10.7222
Max Act: 9.5972. Min Act: -0.1700
Data Index: 6198043 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.7222. Min Range: -10.7222
Max Act: 9.5972. Min Act: -0.1700
Data Index: 4299427 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.7222. Min Range: -10.7222
Max Act: 9.5972. Min Act: -0.1700
Data Index: 8159751 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.7222. Min Range: -10.7222
Max Act: 9.5972. Min Act: -0.1700
Data Index: 4237993 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #19