Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1132 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.4970. Min Range: -12.4970
Max Act: 12.4970. Min Act: -0.1700
Data Index: 6392842 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.4970. Min Range: -12.4970
Max Act: 11.9345. Min Act: -0.1700
Data Index: 4775540 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.4970. Min Range: -12.4970
Max Act: 11.8095. Min Act: -0.1700
Data Index: 200029 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.4970. Min Range: -12.4970
Max Act: 11.7470. Min Act: -0.1700
Data Index: 5915577 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.4970. Min Range: -12.4970
Max Act: 11.8095. Min Act: -0.1700
Data Index: 3617665 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.4970. Min Range: -12.4970
Max Act: 11.7470. Min Act: -0.1700
Data Index: 8225675 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.4970. Min Range: -12.4970
Max Act: 11.6845. Min Act: -0.1700
Data Index: 6392840 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.4970. Min Range: -12.4970
Max Act: 11.6220. Min Act: -0.1700
Data Index: 4097823 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.4970. Min Range: -12.4970
Max Act: 11.6845. Min Act: -0.1700
Data Index: 5678437 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.4970. Min Range: -12.4970
Max Act: 11.6845. Min Act: -0.1700
Data Index: 7025567 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.4970. Min Range: -12.4970
Max Act: 11.6220. Min Act: -0.1700
Data Index: 6526391 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.4970. Min Range: -12.4970
Max Act: 11.6220. Min Act: -0.1700
Data Index: 6987122 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.4970. Min Range: -12.4970
Max Act: 11.5595. Min Act: -0.1700
Data Index: 6263782 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.4970. Min Range: -12.4970
Max Act: 11.5595. Min Act: -0.1700
Data Index: 5200967 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.4970. Min Range: -12.4970
Max Act: 11.4970. Min Act: -0.1700
Data Index: 2455800 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.4970. Min Range: -12.4970
Max Act: 11.4970. Min Act: -0.1700
Data Index: 4386129 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.4970. Min Range: -12.4970
Max Act: 11.5595. Min Act: -0.1700
Data Index: 2430213 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.4970. Min Range: -12.4970
Max Act: 11.4345. Min Act: -0.1700
Data Index: 6137608 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.4970. Min Range: -12.4970
Max Act: 11.4345. Min Act: -0.1700
Data Index: 6962569 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.4970. Min Range: -12.4970
Max Act: 11.4345. Min Act: -0.1700
Data Index: 4640204 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #19