Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4018 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5150. Min Range: -5.5150
Max Act: 5.5150. Min Act: -0.1700
Data Index: 3532843 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5150. Min Range: -5.5150
Max Act: 5.3275. Min Act: -0.1700
Data Index: 2660773 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5150. Min Range: -5.5150
Max Act: 5.2963. Min Act: -0.1700
Data Index: 7540480 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5150. Min Range: -5.5150
Max Act: 5.2338. Min Act: -0.1700
Data Index: 2660772 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5150. Min Range: -5.5150
Max Act: 5.2025. Min Act: -0.1700
Data Index: 7687349 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5150. Min Range: -5.5150
Max Act: 5.2025. Min Act: -0.1700
Data Index: 7589722 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5150. Min Range: -5.5150
Max Act: 5.2025. Min Act: -0.1700
Data Index: 1394030 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5150. Min Range: -5.5150
Max Act: 5.1400. Min Act: -0.1700
Data Index: 1030092 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5150. Min Range: -5.5150
Max Act: 5.1088. Min Act: -0.1700
Data Index: 8567543 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5150. Min Range: -5.5150
Max Act: 5.1088. Min Act: -0.1700
Data Index: 1873482 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5150. Min Range: -5.5150
Max Act: 5.0775. Min Act: -0.1700
Data Index: 7742498 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5150. Min Range: -5.5150
Max Act: 5.1088. Min Act: -0.1700
Data Index: 4800434 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5150. Min Range: -5.5150
Max Act: 5.0775. Min Act: -0.1700
Data Index: 5586651 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5150. Min Range: -5.5150
Max Act: 5.0463. Min Act: -0.1700
Data Index: 7056619 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5150. Min Range: -5.5150
Max Act: 5.0463. Min Act: -0.1700
Data Index: 7170502 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5150. Min Range: -5.5150
Max Act: 4.9838. Min Act: -0.1700
Data Index: 4340720 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5150. Min Range: -5.5150
Max Act: 4.9525. Min Act: -0.1700
Data Index: 3770534 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5150. Min Range: -5.5150
Max Act: 5.0150. Min Act: -0.1700
Data Index: 1821980 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5150. Min Range: -5.5150
Max Act: 4.9525. Min Act: -0.1700
Data Index: 2461462 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5150. Min Range: -5.5150
Max Act: 4.9525. Min Act: -0.1700
Data Index: 3437155 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19