Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3897 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2682. Min Range: -5.2682
Max Act: 5.2682. Min Act: -0.1700
Data Index: 7666396 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2682. Min Range: -5.2682
Max Act: 5.2682. Min Act: -0.1700
Data Index: 7851694 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2682. Min Range: -5.2682
Max Act: 5.2682. Min Act: -0.1700
Data Index: 2020498 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2682. Min Range: -5.2682
Max Act: 5.2057. Min Act: -0.1700
Data Index: 4714642 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2682. Min Range: -5.2682
Max Act: 5.2370. Min Act: -0.1700
Data Index: 3399107 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2682. Min Range: -5.2682
Max Act: 5.2057. Min Act: -0.1700
Data Index: 4952610 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2682. Min Range: -5.2682
Max Act: 5.1432. Min Act: -0.1700
Data Index: 7387626 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2682. Min Range: -5.2682
Max Act: 5.1120. Min Act: -0.1700
Data Index: 4802525 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2682. Min Range: -5.2682
Max Act: 5.1120. Min Act: -0.1700
Data Index: 3874712 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2682. Min Range: -5.2682
Max Act: 5.1120. Min Act: -0.1700
Data Index: 8667818 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2682. Min Range: -5.2682
Max Act: 5.1120. Min Act: -0.1700
Data Index: 6009743 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2682. Min Range: -5.2682
Max Act: 5.0807. Min Act: -0.1700
Data Index: 8667815 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2682. Min Range: -5.2682
Max Act: 5.0807. Min Act: -0.1700
Data Index: 662017 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2682. Min Range: -5.2682
Max Act: 5.0807. Min Act: -0.1700
Data Index: 5305811 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2682. Min Range: -5.2682
Max Act: 5.0495. Min Act: -0.1700
Data Index: 8690647 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2682. Min Range: -5.2682
Max Act: 5.0495. Min Act: -0.1700
Data Index: 8274480 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2682. Min Range: -5.2682
Max Act: 5.0495. Min Act: -0.1700
Data Index: 7293501 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2682. Min Range: -5.2682
Max Act: 5.0495. Min Act: -0.1700
Data Index: 3742240 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2682. Min Range: -5.2682
Max Act: 5.0182. Min Act: -0.1700
Data Index: 4913259 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2682. Min Range: -5.2682
Max Act: 4.9870. Min Act: -0.1700
Data Index: 6905268 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #19