Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3402 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4048. Min Range: -8.4048
Max Act: 8.4048. Min Act: -0.1700
Data Index: 271722 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4048. Min Range: -8.4048
Max Act: 8.2798. Min Act: -0.1700
Data Index: 6478206 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4048. Min Range: -8.4048
Max Act: 8.2173. Min Act: -0.1700
Data Index: 719111 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4048. Min Range: -8.4048
Max Act: 7.9673. Min Act: -0.1700
Data Index: 5393053 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4048. Min Range: -8.4048
Max Act: 7.9673. Min Act: -0.1700
Data Index: 8286702 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4048. Min Range: -8.4048
Max Act: 7.9673. Min Act: -0.1700
Data Index: 6565318 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4048. Min Range: -8.4048
Max Act: 7.9048. Min Act: -0.1700
Data Index: 8090769 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4048. Min Range: -8.4048
Max Act: 7.8423. Min Act: -0.1700
Data Index: 3559965 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4048. Min Range: -8.4048
Max Act: 7.8423. Min Act: -0.1700
Data Index: 5669288 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4048. Min Range: -8.4048
Max Act: 7.7798. Min Act: -0.1700
Data Index: 1856870 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4048. Min Range: -8.4048
Max Act: 7.8111. Min Act: -0.1700
Data Index: 4656 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4048. Min Range: -8.4048
Max Act: 7.8111. Min Act: -0.1700
Data Index: 27457 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4048. Min Range: -8.4048
Max Act: 7.7798. Min Act: -0.1700
Data Index: 4511620 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4048. Min Range: -8.4048
Max Act: 7.7798. Min Act: -0.1700
Data Index: 8756944 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4048. Min Range: -8.4048
Max Act: 7.7798. Min Act: -0.1700
Data Index: 4211424 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4048. Min Range: -8.4048
Max Act: 7.7798. Min Act: -0.1700
Data Index: 2126096 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4048. Min Range: -8.4048
Max Act: 7.7173. Min Act: -0.1700
Data Index: 5531188 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4048. Min Range: -8.4048
Max Act: 7.7486. Min Act: -0.1700
Data Index: 4199413 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4048. Min Range: -8.4048
Max Act: 7.7173. Min Act: -0.1700
Data Index: 4177401 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4048. Min Range: -8.4048
Max Act: 7.6861. Min Act: -0.1700
Data Index: 7137354 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #19