Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3553 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0430. Min Range: -7.0430
Max Act: 7.0430. Min Act: -0.1700
Data Index: 6805483 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0430. Min Range: -7.0430
Max Act: 6.8243. Min Act: -0.1700
Data Index: 8760012 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0430. Min Range: -7.0430
Max Act: 6.8555. Min Act: -0.1700
Data Index: 8103540 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0430. Min Range: -7.0430
Max Act: 6.7930. Min Act: -0.1700
Data Index: 2574026 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0430. Min Range: -7.0430
Max Act: 6.7930. Min Act: -0.1700
Data Index: 369659 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0430. Min Range: -7.0430
Max Act: 6.7618. Min Act: -0.1700
Data Index: 3752888 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0430. Min Range: -7.0430
Max Act: 6.7305. Min Act: -0.1700
Data Index: 1998060 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0430. Min Range: -7.0430
Max Act: 6.7305. Min Act: -0.1700
Data Index: 5261446 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0430. Min Range: -7.0430
Max Act: 6.7305. Min Act: -0.1700
Data Index: 2195191 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0430. Min Range: -7.0430
Max Act: 6.6680. Min Act: -0.1700
Data Index: 8043621 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0430. Min Range: -7.0430
Max Act: 6.6680. Min Act: -0.1700
Data Index: 6351577 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0430. Min Range: -7.0430
Max Act: 6.6680. Min Act: -0.1700
Data Index: 5912533 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0430. Min Range: -7.0430
Max Act: 6.6680. Min Act: -0.1700
Data Index: 8251414 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0430. Min Range: -7.0430
Max Act: 6.6368. Min Act: -0.1700
Data Index: 1228042 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0430. Min Range: -7.0430
Max Act: 6.6368. Min Act: -0.1700
Data Index: 8740814 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0430. Min Range: -7.0430
Max Act: 6.6055. Min Act: -0.1700
Data Index: 2429725 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0430. Min Range: -7.0430
Max Act: 6.5743. Min Act: -0.1700
Data Index: 668397 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0430. Min Range: -7.0430
Max Act: 6.6055. Min Act: -0.1700
Data Index: 8728471 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0430. Min Range: -7.0430
Max Act: 6.5743. Min Act: -0.1700
Data Index: 3430513 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0430. Min Range: -7.0430
Max Act: 6.5743. Min Act: -0.1700
Data Index: 2307762 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #19