Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5575 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9601. Min Range: -5.9601
Max Act: 5.9601. Min Act: -0.1700
Data Index: 1530856 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9601. Min Range: -5.9601
Max Act: 5.9288. Min Act: -0.1700
Data Index: 8306008 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9601. Min Range: -5.9601
Max Act: 5.8976. Min Act: -0.1700
Data Index: 2839896 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9601. Min Range: -5.9601
Max Act: 5.7101. Min Act: -0.1700
Data Index: 4114897 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9601. Min Range: -5.9601
Max Act: 5.6788. Min Act: -0.1700
Data Index: 1035508 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9601. Min Range: -5.9601
Max Act: 5.6476. Min Act: -0.1700
Data Index: 1108403 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9601. Min Range: -5.9601
Max Act: 5.6163. Min Act: -0.1700
Data Index: 8454400 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9601. Min Range: -5.9601
Max Act: 5.5851. Min Act: -0.1700
Data Index: 5031900 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9601. Min Range: -5.9601
Max Act: 5.5851. Min Act: -0.1700
Data Index: 2815925 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9601. Min Range: -5.9601
Max Act: 5.5851. Min Act: -0.1700
Data Index: 6019621 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9601. Min Range: -5.9601
Max Act: 5.5226. Min Act: -0.1700
Data Index: 7379974 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9601. Min Range: -5.9601
Max Act: 5.5226. Min Act: -0.1700
Data Index: 3265892 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9601. Min Range: -5.9601
Max Act: 5.5226. Min Act: -0.1700
Data Index: 5096626 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9601. Min Range: -5.9601
Max Act: 5.5226. Min Act: -0.1700
Data Index: 5966657 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9601. Min Range: -5.9601
Max Act: 5.4913. Min Act: -0.1700
Data Index: 5134020 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9601. Min Range: -5.9601
Max Act: 5.4913. Min Act: -0.1700
Data Index: 5712315 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9601. Min Range: -5.9601
Max Act: 5.4601. Min Act: -0.1700
Data Index: 130215 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9601. Min Range: -5.9601
Max Act: 5.4601. Min Act: -0.1700
Data Index: 6630043 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9601. Min Range: -5.9601
Max Act: 5.4288. Min Act: -0.1700
Data Index: 562285 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9601. Min Range: -5.9601
Max Act: 5.4288. Min Act: -0.1700
Data Index: 2433720 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #19