Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6389 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1974. Min Range: -8.1974
Max Act: 8.1974. Min Act: -0.1700
Data Index: 3814339 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1974. Min Range: -8.1974
Max Act: 8.0724. Min Act: -0.1700
Data Index: 6879585 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1974. Min Range: -8.1974
Max Act: 8.0724. Min Act: -0.1700
Data Index: 3437067 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1974. Min Range: -8.1974
Max Act: 7.9474. Min Act: -0.1700
Data Index: 6962852 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1974. Min Range: -8.1974
Max Act: 8.0099. Min Act: -0.1700
Data Index: 4724628 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1974. Min Range: -8.1974
Max Act: 7.9474. Min Act: -0.1700
Data Index: 3661301 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1974. Min Range: -8.1974
Max Act: 7.9474. Min Act: -0.1700
Data Index: 7086538 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1974. Min Range: -8.1974
Max Act: 7.8849. Min Act: -0.1700
Data Index: 3197496 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1974. Min Range: -8.1974
Max Act: 7.8849. Min Act: -0.1700
Data Index: 2804869 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1974. Min Range: -8.1974
Max Act: 7.8224. Min Act: -0.1700
Data Index: 5149 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1974. Min Range: -8.1974
Max Act: 7.8224. Min Act: -0.1700
Data Index: 2449312 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1974. Min Range: -8.1974
Max Act: 7.7599. Min Act: -0.1700
Data Index: 7662605 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1974. Min Range: -8.1974
Max Act: 7.8224. Min Act: -0.1700
Data Index: 1358287 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1974. Min Range: -8.1974
Max Act: 7.8224. Min Act: -0.1700
Data Index: 8506186 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1974. Min Range: -8.1974
Max Act: 7.8224. Min Act: -0.1700
Data Index: 6497781 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1974. Min Range: -8.1974
Max Act: 7.7599. Min Act: -0.1700
Data Index: 3529709 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1974. Min Range: -8.1974
Max Act: 7.7287. Min Act: -0.1700
Data Index: 2977833 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1974. Min Range: -8.1974
Max Act: 7.6974. Min Act: -0.1700
Data Index: 3998405 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1974. Min Range: -8.1974
Max Act: 7.6974. Min Act: -0.1700
Data Index: 3741107 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1974. Min Range: -8.1974
Max Act: 7.6662. Min Act: -0.1700
Data Index: 5976749 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #19