Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 896 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1059. Min Range: -6.1059
Max Act: 6.1059. Min Act: -0.1700
Data Index: 6828254 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1059. Min Range: -6.1059
Max Act: 5.8871. Min Act: -0.1700
Data Index: 3519694 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1059. Min Range: -6.1059
Max Act: 5.7309. Min Act: -0.1700
Data Index: 3242440 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1059. Min Range: -6.1059
Max Act: 5.6996. Min Act: -0.1700
Data Index: 7467593 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1059. Min Range: -6.1059
Max Act: 5.6996. Min Act: -0.1700
Data Index: 4646082 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1059. Min Range: -6.1059
Max Act: 5.6996. Min Act: -0.1700
Data Index: 8318839 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1059. Min Range: -6.1059
Max Act: 5.6371. Min Act: -0.1700
Data Index: 5913203 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1059. Min Range: -6.1059
Max Act: 5.6371. Min Act: -0.1700
Data Index: 158824 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1059. Min Range: -6.1059
Max Act: 5.6371. Min Act: -0.1700
Data Index: 2806659 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1059. Min Range: -6.1059
Max Act: 5.6371. Min Act: -0.1700
Data Index: 2107826 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1059. Min Range: -6.1059
Max Act: 5.6059. Min Act: -0.1700
Data Index: 3017767 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1059. Min Range: -6.1059
Max Act: 5.6059. Min Act: -0.1700
Data Index: 2989748 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1059. Min Range: -6.1059
Max Act: 5.6059. Min Act: -0.1700
Data Index: 4652709 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1059. Min Range: -6.1059
Max Act: 5.5746. Min Act: -0.1700
Data Index: 4155647 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1059. Min Range: -6.1059
Max Act: 5.5434. Min Act: -0.1700
Data Index: 84758 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1059. Min Range: -6.1059
Max Act: 5.5434. Min Act: -0.1700
Data Index: 1434008 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1059. Min Range: -6.1059
Max Act: 5.5434. Min Act: -0.1700
Data Index: 7228503 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1059. Min Range: -6.1059
Max Act: 5.5121. Min Act: -0.1700
Data Index: 957064 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1059. Min Range: -6.1059
Max Act: 5.5121. Min Act: -0.1700
Data Index: 7730885 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1059. Min Range: -6.1059
Max Act: 5.5121. Min Act: -0.1700
Data Index: 8145541 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #19