Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.7755. Min Range: -2.7755
Max Act: 2.7755. Min Act: -0.1700
Data Index: 4702336 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7755. Min Range: -2.7755
Max Act: 2.7117. Min Act: -0.1700
Data Index: 3509611 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7755. Min Range: -2.7755
Max Act: 2.7117. Min Act: -0.1700
Data Index: 402251 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7755. Min Range: -2.7755
Max Act: 2.7117. Min Act: -0.1700
Data Index: 5018859 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7755. Min Range: -2.7755
Max Act: 2.7117. Min Act: -0.1700
Data Index: 8402155 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7755. Min Range: -2.7755
Max Act: 2.6957. Min Act: -0.1700
Data Index: 7815536 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7755. Min Range: -2.7755
Max Act: 2.6957. Min Act: -0.1700
Data Index: 1695564 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7755. Min Range: -2.7755
Max Act: 2.6957. Min Act: -0.1700
Data Index: 2777442 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7755. Min Range: -2.7755
Max Act: 2.6957. Min Act: -0.1700
Data Index: 2515776 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7755. Min Range: -2.7755
Max Act: 2.6957. Min Act: -0.1700
Data Index: 4517648 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7755. Min Range: -2.7755
Max Act: 2.6957. Min Act: -0.1700
Data Index: 3167333 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7755. Min Range: -2.7755
Max Act: 2.6797. Min Act: -0.1700
Data Index: 8288384 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7755. Min Range: -2.7755
Max Act: 2.6797. Min Act: -0.1700
Data Index: 2941715 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7755. Min Range: -2.7755
Max Act: 2.6797. Min Act: -0.1700
Data Index: 7436298 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7755. Min Range: -2.7755
Max Act: 2.6636. Min Act: -0.1700
Data Index: 8329014 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7755. Min Range: -2.7755
Max Act: 2.6636. Min Act: -0.1700
Data Index: 8675586 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7755. Min Range: -2.7755
Max Act: 2.6636. Min Act: -0.1700
Data Index: 7142139 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7755. Min Range: -2.7755
Max Act: 2.6636. Min Act: -0.1700
Data Index: 1739770 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7755. Min Range: -2.7755
Max Act: 2.6476. Min Act: -0.1700
Data Index: 7169654 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7755. Min Range: -2.7755
Max Act: 2.6476. Min Act: -0.1700
Data Index: 7436299 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #19