Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2739 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6775. Min Range: -7.6775
Max Act: 7.6775. Min Act: -0.1700
Data Index: 7148926 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6775. Min Range: -7.6775
Max Act: 7.3963. Min Act: -0.1700
Data Index: 2171348 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6775. Min Range: -7.6775
Max Act: 7.0525. Min Act: -0.1700
Data Index: 7285746 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6775. Min Range: -7.6775
Max Act: 6.9900. Min Act: -0.1700
Data Index: 6684344 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6775. Min Range: -7.6775
Max Act: 6.9588. Min Act: -0.1700
Data Index: 7940951 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6775. Min Range: -7.6775
Max Act: 6.8963. Min Act: -0.1700
Data Index: 4240505 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6775. Min Range: -7.6775
Max Act: 6.8963. Min Act: -0.1700
Data Index: 3326898 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6775. Min Range: -7.6775
Max Act: 6.8650. Min Act: -0.1700
Data Index: 886975 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6775. Min Range: -7.6775
Max Act: 6.8650. Min Act: -0.1700
Data Index: 7559556 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6775. Min Range: -7.6775
Max Act: 6.8338. Min Act: -0.1700
Data Index: 5139353 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6775. Min Range: -7.6775
Max Act: 6.8338. Min Act: -0.1700
Data Index: 371422 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6775. Min Range: -7.6775
Max Act: 6.8338. Min Act: -0.1700
Data Index: 7465976 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6775. Min Range: -7.6775
Max Act: 6.8025. Min Act: -0.1700
Data Index: 4630018 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6775. Min Range: -7.6775
Max Act: 6.8025. Min Act: -0.1700
Data Index: 1211063 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6775. Min Range: -7.6775
Max Act: 6.8025. Min Act: -0.1700
Data Index: 4283047 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6775. Min Range: -7.6775
Max Act: 6.7400. Min Act: -0.1700
Data Index: 7123453 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6775. Min Range: -7.6775
Max Act: 6.7088. Min Act: -0.1700
Data Index: 2566941 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6775. Min Range: -7.6775
Max Act: 6.7400. Min Act: -0.1700
Data Index: 106266 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6775. Min Range: -7.6775
Max Act: 6.6775. Min Act: -0.1700
Data Index: 7118596 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6775. Min Range: -7.6775
Max Act: 6.7400. Min Act: -0.1700
Data Index: 5061788 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #19