Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3017 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.0793. Min Range: -11.0793
Max Act: 11.0793. Min Act: -0.1700
Data Index: 4792035 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.0793. Min Range: -11.0793
Max Act: 10.9543. Min Act: -0.1700
Data Index: 7305121 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.0793. Min Range: -11.0793
Max Act: 10.9543. Min Act: -0.1700
Data Index: 8729477 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.0793. Min Range: -11.0793
Max Act: 10.8918. Min Act: -0.1700
Data Index: 1644166 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.0793. Min Range: -11.0793
Max Act: 10.8293. Min Act: -0.1700
Data Index: 2662240 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.0793. Min Range: -11.0793
Max Act: 10.8918. Min Act: -0.1700
Data Index: 6428602 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.0793. Min Range: -11.0793
Max Act: 10.7668. Min Act: -0.1700
Data Index: 4063308 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.0793. Min Range: -11.0793
Max Act: 10.7668. Min Act: -0.1700
Data Index: 4404169 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.0793. Min Range: -11.0793
Max Act: 10.7668. Min Act: -0.1700
Data Index: 1871469 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.0793. Min Range: -11.0793
Max Act: 10.6418. Min Act: -0.1700
Data Index: 4400343 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.0793. Min Range: -11.0793
Max Act: 10.6418. Min Act: -0.1700
Data Index: 3854473 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.0793. Min Range: -11.0793
Max Act: 10.6418. Min Act: -0.1700
Data Index: 2212868 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.0793. Min Range: -11.0793
Max Act: 10.7043. Min Act: -0.1700
Data Index: 6949402 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.0793. Min Range: -11.0793
Max Act: 10.6418. Min Act: -0.1700
Data Index: 6960902 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.0793. Min Range: -11.0793
Max Act: 10.5168. Min Act: -0.1700
Data Index: 288939 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.0793. Min Range: -11.0793
Max Act: 10.5793. Min Act: -0.1700
Data Index: 6383054 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.0793. Min Range: -11.0793
Max Act: 10.5793. Min Act: -0.1700
Data Index: 1368573 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.0793. Min Range: -11.0793
Max Act: 10.5793. Min Act: -0.1700
Data Index: 6201959 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.0793. Min Range: -11.0793
Max Act: 10.5168. Min Act: -0.1700
Data Index: 2747584 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.0793. Min Range: -11.0793
Max Act: 10.5168. Min Act: -0.1700
Data Index: 8138791 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #19