Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3027 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7258. Min Range: -3.7258
Max Act: 3.7258. Min Act: -0.1700
Data Index: 6117109 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7258. Min Range: -3.7258
Max Act: 3.7102. Min Act: -0.1700
Data Index: 7113068 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7258. Min Range: -3.7258
Max Act: 3.6476. Min Act: -0.1700
Data Index: 4281106 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7258. Min Range: -3.7258
Max Act: 3.6320. Min Act: -0.1700
Data Index: 4492990 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7258. Min Range: -3.7258
Max Act: 3.6320. Min Act: -0.1700
Data Index: 973478 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7258. Min Range: -3.7258
Max Act: 3.5850. Min Act: -0.1700
Data Index: 8782205 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7258. Min Range: -3.7258
Max Act: 3.5537. Min Act: -0.1700
Data Index: 7226864 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7258. Min Range: -3.7258
Max Act: 3.5850. Min Act: -0.1700
Data Index: 3900715 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7258. Min Range: -3.7258
Max Act: 3.5537. Min Act: -0.1700
Data Index: 4171485 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7258. Min Range: -3.7258
Max Act: 3.5224. Min Act: -0.1700
Data Index: 8454805 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7258. Min Range: -3.7258
Max Act: 3.5224. Min Act: -0.1700
Data Index: 3533384 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7258. Min Range: -3.7258
Max Act: 3.5224. Min Act: -0.1700
Data Index: 5307879 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7258. Min Range: -3.7258
Max Act: 3.5067. Min Act: -0.1700
Data Index: 4571301 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7258. Min Range: -3.7258
Max Act: 3.4911. Min Act: -0.1700
Data Index: 6770820 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7258. Min Range: -3.7258
Max Act: 3.4754. Min Act: -0.1700
Data Index: 8193485 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7258. Min Range: -3.7258
Max Act: 3.4754. Min Act: -0.1700
Data Index: 1655679 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7258. Min Range: -3.7258
Max Act: 3.4441. Min Act: -0.1700
Data Index: 1490528 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7258. Min Range: -3.7258
Max Act: 3.4441. Min Act: -0.1700
Data Index: 829884 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7258. Min Range: -3.7258
Max Act: 3.4284. Min Act: -0.1700
Data Index: 4316976 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7258. Min Range: -3.7258
Max Act: 3.4127. Min Act: -0.1700
Data Index: 6087720 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #19