Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2958 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7447. Min Range: -5.7447
Max Act: 5.7447. Min Act: -0.1700
Data Index: 1160616 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7447. Min Range: -5.7447
Max Act: 5.5572. Min Act: -0.1700
Data Index: 5914875 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7447. Min Range: -5.7447
Max Act: 5.5260. Min Act: -0.1700
Data Index: 5585763 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7447. Min Range: -5.7447
Max Act: 5.5260. Min Act: -0.1700
Data Index: 2573938 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7447. Min Range: -5.7447
Max Act: 5.5260. Min Act: -0.1700
Data Index: 20062 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7447. Min Range: -5.7447
Max Act: 5.4322. Min Act: -0.1700
Data Index: 436674 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7447. Min Range: -5.7447
Max Act: 5.4322. Min Act: -0.1700
Data Index: 4598925 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7447. Min Range: -5.7447
Max Act: 5.4010. Min Act: -0.1700
Data Index: 2367309 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7447. Min Range: -5.7447
Max Act: 5.4010. Min Act: -0.1700
Data Index: 1756275 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7447. Min Range: -5.7447
Max Act: 5.3697. Min Act: -0.1700
Data Index: 6884484 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7447. Min Range: -5.7447
Max Act: 5.3697. Min Act: -0.1700
Data Index: 6735544 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7447. Min Range: -5.7447
Max Act: 5.3385. Min Act: -0.1700
Data Index: 5319428 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7447. Min Range: -5.7447
Max Act: 5.3072. Min Act: -0.1700
Data Index: 1038440 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7447. Min Range: -5.7447
Max Act: 5.2760. Min Act: -0.1700
Data Index: 3144985 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7447. Min Range: -5.7447
Max Act: 5.2447. Min Act: -0.1700
Data Index: 3299821 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7447. Min Range: -5.7447
Max Act: 5.2760. Min Act: -0.1700
Data Index: 8052742 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7447. Min Range: -5.7447
Max Act: 5.2447. Min Act: -0.1700
Data Index: 8455292 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7447. Min Range: -5.7447
Max Act: 5.2447. Min Act: -0.1700
Data Index: 2857840 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7447. Min Range: -5.7447
Max Act: 5.2447. Min Act: -0.1700
Data Index: 2997890 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7447. Min Range: -5.7447
Max Act: 5.1822. Min Act: -0.1700
Data Index: 902742 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #19