Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4276 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8251. Min Range: -4.8251
Max Act: 4.8251. Min Act: -0.1700
Data Index: 2304496 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8251. Min Range: -4.8251
Max Act: 4.7001. Min Act: -0.1700
Data Index: 6549221 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8251. Min Range: -4.8251
Max Act: 4.6376. Min Act: -0.1700
Data Index: 6855693 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8251. Min Range: -4.8251
Max Act: 4.5126. Min Act: -0.1700
Data Index: 7163089 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8251. Min Range: -4.8251
Max Act: 4.4813. Min Act: -0.1700
Data Index: 861125 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8251. Min Range: -4.8251
Max Act: 4.3876. Min Act: -0.1700
Data Index: 5552422 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8251. Min Range: -4.8251
Max Act: 4.3876. Min Act: -0.1700
Data Index: 7668611 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8251. Min Range: -4.8251
Max Act: 4.3876. Min Act: -0.1700
Data Index: 7540604 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8251. Min Range: -4.8251
Max Act: 4.3563. Min Act: -0.1700
Data Index: 2898138 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8251. Min Range: -4.8251
Max Act: 4.3876. Min Act: -0.1700
Data Index: 322143 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8251. Min Range: -4.8251
Max Act: 4.3876. Min Act: -0.1700
Data Index: 305612 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8251. Min Range: -4.8251
Max Act: 4.3876. Min Act: -0.1700
Data Index: 6853140 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8251. Min Range: -4.8251
Max Act: 4.3563. Min Act: -0.1700
Data Index: 5524612 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8251. Min Range: -4.8251
Max Act: 4.3251. Min Act: -0.1700
Data Index: 8429848 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8251. Min Range: -4.8251
Max Act: 4.3251. Min Act: -0.1700
Data Index: 7913828 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8251. Min Range: -4.8251
Max Act: 4.3251. Min Act: -0.1700
Data Index: 3987016 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8251. Min Range: -4.8251
Max Act: 4.3251. Min Act: -0.1700
Data Index: 7687692 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8251. Min Range: -4.8251
Max Act: 4.2938. Min Act: -0.1700
Data Index: 5142625 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8251. Min Range: -4.8251
Max Act: 4.2938. Min Act: -0.1700
Data Index: 1923214 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8251. Min Range: -4.8251
Max Act: 4.2938. Min Act: -0.1700
Data Index: 7900176 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #19