Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6037 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2062. Min Range: -4.2062
Max Act: 4.2062. Min Act: -0.1700
Data Index: 4082607 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2062. Min Range: -4.2062
Max Act: 4.1749. Min Act: -0.1700
Data Index: 4849384 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2062. Min Range: -4.2062
Max Act: 4.1124. Min Act: -0.1700
Data Index: 8494797 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2062. Min Range: -4.2062
Max Act: 4.1124. Min Act: -0.1700
Data Index: 5827350 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2062. Min Range: -4.2062
Max Act: 4.0499. Min Act: -0.1700
Data Index: 2516368 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2062. Min Range: -4.2062
Max Act: 4.0187. Min Act: -0.1700
Data Index: 2976431 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2062. Min Range: -4.2062
Max Act: 3.9561. Min Act: -0.1700
Data Index: 2260848 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2062. Min Range: -4.2062
Max Act: 3.9249. Min Act: -0.1700
Data Index: 7231064 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2062. Min Range: -4.2062
Max Act: 3.9249. Min Act: -0.1700
Data Index: 6197364 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2062. Min Range: -4.2062
Max Act: 3.8936. Min Act: -0.1700
Data Index: 4674587 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2062. Min Range: -4.2062
Max Act: 3.8311. Min Act: -0.1700
Data Index: 7755683 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2062. Min Range: -4.2062
Max Act: 3.8311. Min Act: -0.1700
Data Index: 3691479 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2062. Min Range: -4.2062
Max Act: 3.8311. Min Act: -0.1700
Data Index: 6171853 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2062. Min Range: -4.2062
Max Act: 3.8311. Min Act: -0.1700
Data Index: 4082608 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2062. Min Range: -4.2062
Max Act: 3.7685. Min Act: -0.1700
Data Index: 8637373 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2062. Min Range: -4.2062
Max Act: 3.7998. Min Act: -0.1700
Data Index: 8420396 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2062. Min Range: -4.2062
Max Act: 3.7685. Min Act: -0.1700
Data Index: 267387 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2062. Min Range: -4.2062
Max Act: 3.7998. Min Act: -0.1700
Data Index: 5663633 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2062. Min Range: -4.2062
Max Act: 3.7685. Min Act: -0.1700
Data Index: 6258950 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2062. Min Range: -4.2062
Max Act: 3.7685. Min Act: -0.1700
Data Index: 6611960 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #19