Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3087 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.7680. Min Range: -2.7680
Max Act: 2.7680. Min Act: -0.1700
Data Index: 8378032 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7680. Min Range: -2.7680
Max Act: 2.7201. Min Act: -0.1700
Data Index: 4564182 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7680. Min Range: -2.7680
Max Act: 2.7042. Min Act: -0.1700
Data Index: 3937807 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7680. Min Range: -2.7680
Max Act: 2.7042. Min Act: -0.1700
Data Index: 4452446 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7680. Min Range: -2.7680
Max Act: 2.6721. Min Act: -0.1700
Data Index: 1254983 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7680. Min Range: -2.7680
Max Act: 2.6240. Min Act: -0.1700
Data Index: 3776272 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7680. Min Range: -2.7680
Max Act: 2.6240. Min Act: -0.1700
Data Index: 2586084 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7680. Min Range: -2.7680
Max Act: 2.5757. Min Act: -0.1700
Data Index: 3165948 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7680. Min Range: -2.7680
Max Act: 2.5757. Min Act: -0.1700
Data Index: 7920475 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7680. Min Range: -2.7680
Max Act: 2.5918. Min Act: -0.1700
Data Index: 6229260 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7680. Min Range: -2.7680
Max Act: 2.5757. Min Act: -0.1700
Data Index: 1118582 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7680. Min Range: -2.7680
Max Act: 2.5596. Min Act: -0.1700
Data Index: 1038961 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7680. Min Range: -2.7680
Max Act: 2.5596. Min Act: -0.1700
Data Index: 8607382 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7680. Min Range: -2.7680
Max Act: 2.5596. Min Act: -0.1700
Data Index: 6893296 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7680. Min Range: -2.7680
Max Act: 2.5596. Min Act: -0.1700
Data Index: 1134960 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7680. Min Range: -2.7680
Max Act: 2.5273. Min Act: -0.1700
Data Index: 7634813 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7680. Min Range: -2.7680
Max Act: 2.5596. Min Act: -0.1700
Data Index: 5817651 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7680. Min Range: -2.7680
Max Act: 2.5434. Min Act: -0.1700
Data Index: 4339983 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7680. Min Range: -2.7680
Max Act: 2.5434. Min Act: -0.1700
Data Index: 6259191 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7680. Min Range: -2.7680
Max Act: 2.5273. Min Act: -0.1700
Data Index: 2555567 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #19