Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2739 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1211. Min Range: -9.1211
Max Act: 9.1211. Min Act: -0.1700
Data Index: 2102303 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1211. Min Range: -9.1211
Max Act: 8.9336. Min Act: -0.1700
Data Index: 1831543 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1211. Min Range: -9.1211
Max Act: 8.6211. Min Act: -0.1700
Data Index: 3121137 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1211. Min Range: -9.1211
Max Act: 8.5586. Min Act: -0.1700
Data Index: 159498 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1211. Min Range: -9.1211
Max Act: 8.4961. Min Act: -0.1700
Data Index: 1974127 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1211. Min Range: -9.1211
Max Act: 8.4961. Min Act: -0.1700
Data Index: 932231 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1211. Min Range: -9.1211
Max Act: 8.3711. Min Act: -0.1700
Data Index: 1492071 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1211. Min Range: -9.1211
Max Act: 8.3711. Min Act: -0.1700
Data Index: 1580708 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1211. Min Range: -9.1211
Max Act: 8.3086. Min Act: -0.1700
Data Index: 790270 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1211. Min Range: -9.1211
Max Act: 8.3086. Min Act: -0.1700
Data Index: 2274904 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1211. Min Range: -9.1211
Max Act: 8.2461. Min Act: -0.1700
Data Index: 5607899 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1211. Min Range: -9.1211
Max Act: 8.2461. Min Act: -0.1700
Data Index: 633009 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1211. Min Range: -9.1211
Max Act: 8.2461. Min Act: -0.1700
Data Index: 3491838 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1211. Min Range: -9.1211
Max Act: 8.1836. Min Act: -0.1700
Data Index: 6858302 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1211. Min Range: -9.1211
Max Act: 8.1836. Min Act: -0.1700
Data Index: 4849370 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1211. Min Range: -9.1211
Max Act: 8.1836. Min Act: -0.1700
Data Index: 2273252 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1211. Min Range: -9.1211
Max Act: 8.1836. Min Act: -0.1700
Data Index: 5612289 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1211. Min Range: -9.1211
Max Act: 8.1836. Min Act: -0.1700
Data Index: 753608 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1211. Min Range: -9.1211
Max Act: 8.1211. Min Act: -0.1700
Data Index: 2206113 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1211. Min Range: -9.1211
Max Act: 8.1211. Min Act: -0.1700
Data Index: 6855839 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #19