Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3172 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0633. Min Range: -9.0633
Max Act: 9.0633. Min Act: -0.1700
Data Index: 7785867 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0633. Min Range: -9.0633
Max Act: 8.8758. Min Act: -0.1700
Data Index: 5571942 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0633. Min Range: -9.0633
Max Act: 8.0008. Min Act: -0.1700
Data Index: 42260 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0633. Min Range: -9.0633
Max Act: 8.0008. Min Act: -0.1699
Data Index: 4954518 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0633. Min Range: -9.0633
Max Act: 8.0320. Min Act: -0.1700
Data Index: 8463298 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0633. Min Range: -9.0633
Max Act: 8.0008. Min Act: -0.1700
Data Index: 4954508 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0633. Min Range: -9.0633
Max Act: 7.9383. Min Act: -0.1700
Data Index: 2121171 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0633. Min Range: -9.0633
Max Act: 7.9695. Min Act: -0.1700
Data Index: 2962171 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0633. Min Range: -9.0633
Max Act: 7.9695. Min Act: -0.1700
Data Index: 1492419 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0633. Min Range: -9.0633
Max Act: 7.9070. Min Act: -0.1700
Data Index: 5343343 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0633. Min Range: -9.0633
Max Act: 7.9383. Min Act: -0.1700
Data Index: 4380204 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0633. Min Range: -9.0633
Max Act: 7.9383. Min Act: -0.1700
Data Index: 4246554 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0633. Min Range: -9.0633
Max Act: 7.9070. Min Act: -0.1700
Data Index: 8621526 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0633. Min Range: -9.0633
Max Act: 7.8758. Min Act: -0.1700
Data Index: 6924751 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0633. Min Range: -9.0633
Max Act: 7.9070. Min Act: -0.1700
Data Index: 8690273 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0633. Min Range: -9.0633
Max Act: 7.8445. Min Act: -0.1700
Data Index: 1302467 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0633. Min Range: -9.0633
Max Act: 7.8133. Min Act: -0.1700
Data Index: 7690598 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0633. Min Range: -9.0633
Max Act: 7.8133. Min Act: -0.1700
Data Index: 4297474 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0633. Min Range: -9.0633
Max Act: 7.8133. Min Act: -0.1700
Data Index: 5240013 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0633. Min Range: -9.0633
Max Act: 7.7820. Min Act: -0.1700
Data Index: 308583 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #19