Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 639 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2053. Min Range: -5.2053
Max Act: 5.2053. Min Act: -0.1700
Data Index: 3291835 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2053. Min Range: -5.2053
Max Act: 5.0491. Min Act: -0.1700
Data Index: 6939976 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2053. Min Range: -5.2053
Max Act: 5.0178. Min Act: -0.1700
Data Index: 1765467 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2053. Min Range: -5.2053
Max Act: 5.0178. Min Act: -0.1700
Data Index: 6939980 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2053. Min Range: -5.2053
Max Act: 4.9866. Min Act: -0.1700
Data Index: 6939974 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2053. Min Range: -5.2053
Max Act: 4.9866. Min Act: -0.1700
Data Index: 3006450 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2053. Min Range: -5.2053
Max Act: 4.9866. Min Act: -0.1700
Data Index: 6939968 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2053. Min Range: -5.2053
Max Act: 4.9553. Min Act: -0.1700
Data Index: 8800202 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2053. Min Range: -5.2053
Max Act: 4.9553. Min Act: -0.1700
Data Index: 3291836 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2053. Min Range: -5.2053
Max Act: 4.9241. Min Act: -0.1700
Data Index: 5197797 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2053. Min Range: -5.2053
Max Act: 4.9241. Min Act: -0.1700
Data Index: 3006451 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2053. Min Range: -5.2053
Max Act: 4.9241. Min Act: -0.1700
Data Index: 8516017 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2053. Min Range: -5.2053
Max Act: 4.8928. Min Act: -0.1700
Data Index: 3907302 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2053. Min Range: -5.2053
Max Act: 4.8928. Min Act: -0.1700
Data Index: 3907304 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2053. Min Range: -5.2053
Max Act: 4.8928. Min Act: -0.1700
Data Index: 8759324 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2053. Min Range: -5.2053
Max Act: 4.8928. Min Act: -0.1700
Data Index: 7501808 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2053. Min Range: -5.2053
Max Act: 4.8928. Min Act: -0.1700
Data Index: 3291837 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2053. Min Range: -5.2053
Max Act: 4.8928. Min Act: -0.1700
Data Index: 2785886 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2053. Min Range: -5.2053
Max Act: 4.8616. Min Act: -0.1700
Data Index: 3907307 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2053. Min Range: -5.2053
Max Act: 4.8616. Min Act: -0.1700
Data Index: 553078 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #19