Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3554 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3894. Min Range: -4.3894
Max Act: 4.3894. Min Act: -0.1700
Data Index: 2584935 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3894. Min Range: -4.3894
Max Act: 4.0457. Min Act: -0.1700
Data Index: 8022021 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3894. Min Range: -4.3894
Max Act: 3.8581. Min Act: -0.1700
Data Index: 2252108 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3894. Min Range: -4.3894
Max Act: 3.8737. Min Act: -0.1700
Data Index: 6048769 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3894. Min Range: -4.3894
Max Act: 3.7955. Min Act: -0.1700
Data Index: 7992538 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3894. Min Range: -4.3894
Max Act: 3.8112. Min Act: -0.1700
Data Index: 355016 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3894. Min Range: -4.3894
Max Act: 3.7799. Min Act: -0.1700
Data Index: 8709911 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3894. Min Range: -4.3894
Max Act: 3.7643. Min Act: -0.1700
Data Index: 6349760 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3894. Min Range: -4.3894
Max Act: 3.7330. Min Act: -0.1700
Data Index: 6349759 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3894. Min Range: -4.3894
Max Act: 3.7173. Min Act: -0.1700
Data Index: 2190747 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3894. Min Range: -4.3894
Max Act: 3.7017. Min Act: -0.1700
Data Index: 224851 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3894. Min Range: -4.3894
Max Act: 3.7017. Min Act: -0.1700
Data Index: 5628230 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3894. Min Range: -4.3894
Max Act: 3.6860. Min Act: -0.1700
Data Index: 8253279 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3894. Min Range: -4.3894
Max Act: 3.6548. Min Act: -0.1700
Data Index: 7205848 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3894. Min Range: -4.3894
Max Act: 3.6235. Min Act: -0.1700
Data Index: 2200908 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3894. Min Range: -4.3894
Max Act: 3.6391. Min Act: -0.1700
Data Index: 99605 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3894. Min Range: -4.3894
Max Act: 3.6235. Min Act: -0.1700
Data Index: 2730515 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3894. Min Range: -4.3894
Max Act: 3.6235. Min Act: -0.1700
Data Index: 3621573 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3894. Min Range: -4.3894
Max Act: 3.6235. Min Act: -0.1700
Data Index: 4675133 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3894. Min Range: -4.3894
Max Act: 3.6078. Min Act: -0.1700
Data Index: 7444227 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #19