Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4099 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9759. Min Range: -6.9759
Max Act: 6.9759. Min Act: -0.1700
Data Index: 6121009 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9759. Min Range: -6.9759
Max Act: 6.8509. Min Act: -0.1700
Data Index: 4427934 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9759. Min Range: -6.9759
Max Act: 6.8196. Min Act: -0.1700
Data Index: 7531336 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9759. Min Range: -6.9759
Max Act: 6.7884. Min Act: -0.1700
Data Index: 7554976 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9759. Min Range: -6.9759
Max Act: 6.7259. Min Act: -0.1700
Data Index: 5551498 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9759. Min Range: -6.9759
Max Act: 6.7571. Min Act: -0.1700
Data Index: 7264513 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9759. Min Range: -6.9759
Max Act: 6.7571. Min Act: -0.1700
Data Index: 1907620 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9759. Min Range: -6.9759
Max Act: 6.7571. Min Act: -0.1700
Data Index: 4107482 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9759. Min Range: -6.9759
Max Act: 6.7259. Min Act: -0.1700
Data Index: 8586858 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9759. Min Range: -6.9759
Max Act: 6.7259. Min Act: -0.1700
Data Index: 8591846 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9759. Min Range: -6.9759
Max Act: 6.7571. Min Act: -0.1700
Data Index: 6014352 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9759. Min Range: -6.9759
Max Act: 6.6946. Min Act: -0.1700
Data Index: 4456990 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9759. Min Range: -6.9759
Max Act: 6.6946. Min Act: -0.1700
Data Index: 1307511 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9759. Min Range: -6.9759
Max Act: 6.6634. Min Act: -0.1700
Data Index: 2241534 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9759. Min Range: -6.9759
Max Act: 6.6009. Min Act: -0.1700
Data Index: 1518518 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9759. Min Range: -6.9759
Max Act: 6.5696. Min Act: -0.1700
Data Index: 706721 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9759. Min Range: -6.9759
Max Act: 6.5696. Min Act: -0.1700
Data Index: 7988260 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9759. Min Range: -6.9759
Max Act: 6.5696. Min Act: -0.1700
Data Index: 105743 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9759. Min Range: -6.9759
Max Act: 6.5696. Min Act: -0.1700
Data Index: 5964500 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9759. Min Range: -6.9759
Max Act: 6.5071. Min Act: -0.1700
Data Index: 2448298 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #19