Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5679 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1039. Min Range: -5.1039
Max Act: 5.1039. Min Act: -0.1700
Data Index: 6170695 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1039. Min Range: -5.1039
Max Act: 5.0101. Min Act: -0.1700
Data Index: 6038550 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1039. Min Range: -5.1039
Max Act: 5.0101. Min Act: -0.1700
Data Index: 1339643 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1039. Min Range: -5.1039
Max Act: 5.0101. Min Act: -0.1700
Data Index: 1456128 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1039. Min Range: -5.1039
Max Act: 4.9164. Min Act: -0.1700
Data Index: 5397453 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1039. Min Range: -5.1039
Max Act: 4.8539. Min Act: -0.1700
Data Index: 6132238 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1039. Min Range: -5.1039
Max Act: 4.8226. Min Act: -0.1700
Data Index: 8267046 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1039. Min Range: -5.1039
Max Act: 4.8226. Min Act: -0.1700
Data Index: 8265190 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1039. Min Range: -5.1039
Max Act: 4.8226. Min Act: -0.1700
Data Index: 3045934 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1039. Min Range: -5.1039
Max Act: 4.7914. Min Act: -0.1700
Data Index: 1112568 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1039. Min Range: -5.1039
Max Act: 4.7914. Min Act: -0.1700
Data Index: 187330 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1039. Min Range: -5.1039
Max Act: 4.7601. Min Act: -0.1700
Data Index: 4538270 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1039. Min Range: -5.1039
Max Act: 4.7914. Min Act: -0.1700
Data Index: 2706855 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1039. Min Range: -5.1039
Max Act: 4.7914. Min Act: -0.1700
Data Index: 6769959 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1039. Min Range: -5.1039
Max Act: 4.7601. Min Act: -0.1700
Data Index: 3984065 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1039. Min Range: -5.1039
Max Act: 4.7914. Min Act: -0.1700
Data Index: 3045933 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1039. Min Range: -5.1039
Max Act: 4.7601. Min Act: -0.1700
Data Index: 916629 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1039. Min Range: -5.1039
Max Act: 4.7601. Min Act: -0.1700
Data Index: 3376427 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1039. Min Range: -5.1039
Max Act: 4.7601. Min Act: -0.1700
Data Index: 149914 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1039. Min Range: -5.1039
Max Act: 4.7601. Min Act: -0.1700
Data Index: 3151663 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #19