Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 634 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7896. Min Range: -7.7896
Max Act: 7.7896. Min Act: -0.1697
Data Index: 3052847 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7896. Min Range: -7.7896
Max Act: 7.7271. Min Act: -0.1700
Data Index: 1606606 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7896. Min Range: -7.7896
Max Act: 7.6021. Min Act: -0.1700
Data Index: 377490 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7896. Min Range: -7.7896
Max Act: 7.6021. Min Act: -0.1700
Data Index: 1909147 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7896. Min Range: -7.7896
Max Act: 7.5396. Min Act: -0.1700
Data Index: 6650637 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7896. Min Range: -7.7896
Max Act: 7.5396. Min Act: -0.1700
Data Index: 7379023 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7896. Min Range: -7.7896
Max Act: 7.4771. Min Act: -0.1700
Data Index: 3834290 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7896. Min Range: -7.7896
Max Act: 7.5396. Min Act: -0.1700
Data Index: 1338768 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7896. Min Range: -7.7896
Max Act: 7.5396. Min Act: -0.1700
Data Index: 7569859 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7896. Min Range: -7.7896
Max Act: 7.5396. Min Act: -0.1700
Data Index: 5123904 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7896. Min Range: -7.7896
Max Act: 7.5396. Min Act: -0.1700
Data Index: 249987 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7896. Min Range: -7.7896
Max Act: 7.4771. Min Act: -0.1700
Data Index: 8410352 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7896. Min Range: -7.7896
Max Act: 7.5396. Min Act: -0.1700
Data Index: 5655418 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7896. Min Range: -7.7896
Max Act: 7.4771. Min Act: -0.1700
Data Index: 3856248 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7896. Min Range: -7.7896
Max Act: 7.4771. Min Act: -0.1700
Data Index: 466309 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7896. Min Range: -7.7896
Max Act: 7.4771. Min Act: -0.1699
Data Index: 8358923 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7896. Min Range: -7.7896
Max Act: 7.4146. Min Act: -0.1700
Data Index: 8003282 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7896. Min Range: -7.7896
Max Act: 7.4771. Min Act: -0.1700
Data Index: 2838837 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7896. Min Range: -7.7896
Max Act: 7.4771. Min Act: -0.1700
Data Index: 1056803 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7896. Min Range: -7.7896
Max Act: 7.4771. Min Act: -0.1700
Data Index: 6463581 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #19