Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6327 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3978. Min Range: -8.3978
Max Act: 8.3978. Min Act: -0.1700
Data Index: 8068081 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3978. Min Range: -8.3978
Max Act: 8.2728. Min Act: -0.1700
Data Index: 2031972 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3978. Min Range: -8.3978
Max Act: 8.2103. Min Act: -0.1700
Data Index: 512619 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3978. Min Range: -8.3978
Max Act: 8.1478. Min Act: -0.1700
Data Index: 4805688 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3978. Min Range: -8.3978
Max Act: 8.1478. Min Act: -0.1700
Data Index: 1232825 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3978. Min Range: -8.3978
Max Act: 8.0853. Min Act: -0.1700
Data Index: 8805609 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3978. Min Range: -8.3978
Max Act: 8.0853. Min Act: -0.1700
Data Index: 1542750 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3978. Min Range: -8.3978
Max Act: 8.0228. Min Act: -0.1700
Data Index: 1461579 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3978. Min Range: -8.3978
Max Act: 8.0228. Min Act: -0.1700
Data Index: 1538651 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3978. Min Range: -8.3978
Max Act: 8.0228. Min Act: -0.1700
Data Index: 1701438 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3978. Min Range: -8.3978
Max Act: 7.9603. Min Act: -0.1700
Data Index: 4900150 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3978. Min Range: -8.3978
Max Act: 7.9603. Min Act: -0.1700
Data Index: 5609209 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3978. Min Range: -8.3978
Max Act: 7.9603. Min Act: -0.1700
Data Index: 5018497 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3978. Min Range: -8.3978
Max Act: 7.9603. Min Act: -0.1700
Data Index: 6092022 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3978. Min Range: -8.3978
Max Act: 7.9603. Min Act: -0.1700
Data Index: 6232405 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3978. Min Range: -8.3978
Max Act: 7.9603. Min Act: -0.1700
Data Index: 3179510 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3978. Min Range: -8.3978
Max Act: 7.9603. Min Act: -0.1700
Data Index: 2733046 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3978. Min Range: -8.3978
Max Act: 7.9603. Min Act: -0.1700
Data Index: 2553977 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3978. Min Range: -8.3978
Max Act: 7.8978. Min Act: -0.1700
Data Index: 349887 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3978. Min Range: -8.3978
Max Act: 7.8978. Min Act: -0.1700
Data Index: 6007603 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #19