Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4265 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8504. Min Range: -9.8504
Max Act: 9.8504. Min Act: -0.1700
Data Index: 2456890 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8504. Min Range: -9.8504
Max Act: 9.8504. Min Act: -0.1700
Data Index: 5697995 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8504. Min Range: -9.8504
Max Act: 9.7254. Min Act: -0.1700
Data Index: 453136 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8504. Min Range: -9.8504
Max Act: 9.6629. Min Act: -0.1700
Data Index: 1858600 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8504. Min Range: -9.8504
Max Act: 9.6629. Min Act: -0.1700
Data Index: 1963729 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8504. Min Range: -9.8504
Max Act: 9.6629. Min Act: -0.1700
Data Index: 1861288 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8504. Min Range: -9.8504
Max Act: 9.6629. Min Act: -0.1700
Data Index: 4470097 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8504. Min Range: -9.8504
Max Act: 9.6629. Min Act: -0.1700
Data Index: 5110601 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8504. Min Range: -9.8504
Max Act: 9.6004. Min Act: -0.1700
Data Index: 3133704 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8504. Min Range: -9.8504
Max Act: 9.5379. Min Act: -0.1700
Data Index: 4603976 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8504. Min Range: -9.8504
Max Act: 9.4754. Min Act: -0.1700
Data Index: 7966272 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8504. Min Range: -9.8504
Max Act: 9.4754. Min Act: -0.1700
Data Index: 5621804 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8504. Min Range: -9.8504
Max Act: 9.4129. Min Act: -0.1700
Data Index: 8411138 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8504. Min Range: -9.8504
Max Act: 9.4754. Min Act: -0.1700
Data Index: 8073813 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8504. Min Range: -9.8504
Max Act: 9.4754. Min Act: -0.1700
Data Index: 2019270 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8504. Min Range: -9.8504
Max Act: 9.4129. Min Act: -0.1700
Data Index: 5719817 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8504. Min Range: -9.8504
Max Act: 9.4129. Min Act: -0.1700
Data Index: 6101387 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8504. Min Range: -9.8504
Max Act: 9.4754. Min Act: -0.1700
Data Index: 3830174 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8504. Min Range: -9.8504
Max Act: 9.4129. Min Act: -0.1700
Data Index: 1069424 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8504. Min Range: -9.8504
Max Act: 9.4129. Min Act: -0.1700
Data Index: 927268 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #19