Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3574 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2614. Min Range: -4.2614
Max Act: 4.2614. Min Act: -0.1700
Data Index: 3888029 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2614. Min Range: -4.2614
Max Act: 4.1051. Min Act: -0.1700
Data Index: 2036239 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2614. Min Range: -4.2614
Max Act: 4.0426. Min Act: -0.1700
Data Index: 8044222 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2614. Min Range: -4.2614
Max Act: 4.0113. Min Act: -0.1700
Data Index: 4626937 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2614. Min Range: -4.2614
Max Act: 3.9019. Min Act: -0.1700
Data Index: 5927944 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2614. Min Range: -4.2614
Max Act: 3.9175. Min Act: -0.1700
Data Index: 8560023 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2614. Min Range: -4.2614
Max Act: 3.9175. Min Act: -0.1700
Data Index: 8047643 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2614. Min Range: -4.2614
Max Act: 3.9019. Min Act: -0.1700
Data Index: 6137432 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2614. Min Range: -4.2614
Max Act: 3.9019. Min Act: -0.1700
Data Index: 6523088 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2614. Min Range: -4.2614
Max Act: 3.8863. Min Act: -0.1700
Data Index: 7945304 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2614. Min Range: -4.2614
Max Act: 3.8550. Min Act: -0.1700
Data Index: 4359253 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2614. Min Range: -4.2614
Max Act: 3.8550. Min Act: -0.1700
Data Index: 2089661 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2614. Min Range: -4.2614
Max Act: 3.8394. Min Act: -0.1700
Data Index: 3657852 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2614. Min Range: -4.2614
Max Act: 3.8237. Min Act: -0.1700
Data Index: 8054569 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2614. Min Range: -4.2614
Max Act: 3.7925. Min Act: -0.1700
Data Index: 6594524 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2614. Min Range: -4.2614
Max Act: 3.8081. Min Act: -0.1700
Data Index: 3547576 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2614. Min Range: -4.2614
Max Act: 3.7925. Min Act: -0.1700
Data Index: 3657449 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2614. Min Range: -4.2614
Max Act: 3.7768. Min Act: -0.1700
Data Index: 6406779 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2614. Min Range: -4.2614
Max Act: 3.7925. Min Act: -0.1700
Data Index: 2188042 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2614. Min Range: -4.2614
Max Act: 3.7925. Min Act: -0.1700
Data Index: 1572556 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #19