Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2781 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5672. Min Range: -5.5672
Max Act: 5.5672. Min Act: -0.1700
Data Index: 8707425 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5672. Min Range: -5.5672
Max Act: 5.5047. Min Act: -0.1700
Data Index: 6929665 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5672. Min Range: -5.5672
Max Act: 5.4109. Min Act: -0.1700
Data Index: 980741 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5672. Min Range: -5.5672
Max Act: 5.3484. Min Act: -0.1700
Data Index: 7538771 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5672. Min Range: -5.5672
Max Act: 5.3172. Min Act: -0.1700
Data Index: 6002821 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5672. Min Range: -5.5672
Max Act: 5.2859. Min Act: -0.1700
Data Index: 313780 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5672. Min Range: -5.5672
Max Act: 5.1922. Min Act: -0.1700
Data Index: 5571757 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5672. Min Range: -5.5672
Max Act: 5.1922. Min Act: -0.1700
Data Index: 6515382 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5672. Min Range: -5.5672
Max Act: 5.1922. Min Act: -0.1700
Data Index: 2844812 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5672. Min Range: -5.5672
Max Act: 5.1609. Min Act: -0.1700
Data Index: 8177362 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5672. Min Range: -5.5672
Max Act: 5.1609. Min Act: -0.1700
Data Index: 5658839 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5672. Min Range: -5.5672
Max Act: 5.1297. Min Act: -0.1700
Data Index: 4828891 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5672. Min Range: -5.5672
Max Act: 5.1297. Min Act: -0.1700
Data Index: 206381 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5672. Min Range: -5.5672
Max Act: 5.1297. Min Act: -0.1700
Data Index: 1230533 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5672. Min Range: -5.5672
Max Act: 5.0984. Min Act: -0.1700
Data Index: 771365 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5672. Min Range: -5.5672
Max Act: 5.0984. Min Act: -0.1700
Data Index: 3996425 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5672. Min Range: -5.5672
Max Act: 5.0672. Min Act: -0.1700
Data Index: 5215892 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5672. Min Range: -5.5672
Max Act: 5.0984. Min Act: -0.1700
Data Index: 194667 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5672. Min Range: -5.5672
Max Act: 5.0984. Min Act: -0.1700
Data Index: 3999672 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5672. Min Range: -5.5672
Max Act: 5.0359. Min Act: -0.1700
Data Index: 5468709 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #19