Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4542 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6620. Min Range: -3.6620
Max Act: 3.6620. Min Act: -0.1700
Data Index: 7977702 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6620. Min Range: -3.6620
Max Act: 3.5837. Min Act: -0.1700
Data Index: 3120360 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6620. Min Range: -3.6620
Max Act: 3.5994. Min Act: -0.1700
Data Index: 7671631 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6620. Min Range: -3.6620
Max Act: 3.5681. Min Act: -0.1700
Data Index: 4551740 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6620. Min Range: -3.6620
Max Act: 3.5368. Min Act: -0.1700
Data Index: 3120359 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6620. Min Range: -3.6620
Max Act: 3.5211. Min Act: -0.1700
Data Index: 348771 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6620. Min Range: -3.6620
Max Act: 3.4741. Min Act: -0.1700
Data Index: 8404379 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6620. Min Range: -3.6620
Max Act: 3.4741. Min Act: -0.1700
Data Index: 6812875 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6620. Min Range: -3.6620
Max Act: 3.4428. Min Act: -0.1700
Data Index: 6156599 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6620. Min Range: -3.6620
Max Act: 3.3644. Min Act: -0.1700
Data Index: 3993799 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6620. Min Range: -3.6620
Max Act: 3.3644. Min Act: -0.1700
Data Index: 3899781 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6620. Min Range: -3.6620
Max Act: 3.3644. Min Act: -0.1700
Data Index: 6398683 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6620. Min Range: -3.6620
Max Act: 3.3487. Min Act: -0.1700
Data Index: 4717491 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6620. Min Range: -3.6620
Max Act: 3.3487. Min Act: -0.1700
Data Index: 8738707 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6620. Min Range: -3.6620
Max Act: 3.3487. Min Act: -0.1700
Data Index: 1209455 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6620. Min Range: -3.6620
Max Act: 3.3330. Min Act: -0.1700
Data Index: 4874955 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6620. Min Range: -3.6620
Max Act: 3.3330. Min Act: -0.1700
Data Index: 8724176 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6620. Min Range: -3.6620
Max Act: 3.3330. Min Act: -0.1700
Data Index: 8573965 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6620. Min Range: -3.6620
Max Act: 3.3173. Min Act: -0.1700
Data Index: 5374793 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6620. Min Range: -3.6620
Max Act: 3.2859. Min Act: -0.1700
Data Index: 1570838 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #19