Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3481 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6535. Min Range: -5.6535
Max Act: 5.6535. Min Act: -0.1700
Data Index: 386866 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6535. Min Range: -5.6535
Max Act: 5.6535. Min Act: -0.1700
Data Index: 7216278 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6535. Min Range: -5.6535
Max Act: 5.6535. Min Act: -0.1700
Data Index: 335440 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6535. Min Range: -5.6535
Max Act: 5.5910. Min Act: -0.1700
Data Index: 6522271 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6535. Min Range: -5.6535
Max Act: 5.6222. Min Act: -0.1700
Data Index: 5978306 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6535. Min Range: -5.6535
Max Act: 5.6535. Min Act: -0.1700
Data Index: 3825804 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6535. Min Range: -5.6535
Max Act: 5.5910. Min Act: -0.1700
Data Index: 2523563 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6535. Min Range: -5.6535
Max Act: 5.5910. Min Act: -0.1700
Data Index: 8800137 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6535. Min Range: -5.6535
Max Act: 5.5910. Min Act: -0.1700
Data Index: 208613 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6535. Min Range: -5.6535
Max Act: 5.5910. Min Act: -0.1700
Data Index: 2190004 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6535. Min Range: -5.6535
Max Act: 5.5597. Min Act: -0.1700
Data Index: 6853268 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6535. Min Range: -5.6535
Max Act: 5.5597. Min Act: -0.1700
Data Index: 5400645 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6535. Min Range: -5.6535
Max Act: 5.5597. Min Act: -0.1700
Data Index: 51082 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6535. Min Range: -5.6535
Max Act: 5.5285. Min Act: -0.1700
Data Index: 5451799 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6535. Min Range: -5.6535
Max Act: 5.5285. Min Act: -0.1700
Data Index: 7822470 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6535. Min Range: -5.6535
Max Act: 5.5285. Min Act: -0.1700
Data Index: 6727612 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6535. Min Range: -5.6535
Max Act: 5.5285. Min Act: -0.1700
Data Index: 6786354 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6535. Min Range: -5.6535
Max Act: 5.5285. Min Act: -0.1700
Data Index: 2791431 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6535. Min Range: -5.6535
Max Act: 5.5285. Min Act: -0.1700
Data Index: 8620289 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6535. Min Range: -5.6535
Max Act: 5.4972. Min Act: -0.1700
Data Index: 5671060 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #19