Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5564 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0125. Min Range: -3.0125
Max Act: 3.0125. Min Act: -0.1700
Data Index: 6592733 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0125. Min Range: -3.0125
Max Act: 3.0125. Min Act: -0.1700
Data Index: 3325851 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0125. Min Range: -3.0125
Max Act: 2.9493. Min Act: -0.1700
Data Index: 8706987 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0125. Min Range: -3.0125
Max Act: 2.9176. Min Act: -0.1700
Data Index: 8439725 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0125. Min Range: -3.0125
Max Act: 2.9017. Min Act: -0.1700
Data Index: 2805740 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0125. Min Range: -3.0125
Max Act: 2.9017. Min Act: -0.1700
Data Index: 1449412 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0125. Min Range: -3.0125
Max Act: 2.9017. Min Act: -0.1700
Data Index: 2380871 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0125. Min Range: -3.0125
Max Act: 2.9017. Min Act: -0.1700
Data Index: 3696196 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0125. Min Range: -3.0125
Max Act: 2.9017. Min Act: -0.1700
Data Index: 3762890 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0125. Min Range: -3.0125
Max Act: 2.8700. Min Act: -0.1700
Data Index: 4184084 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0125. Min Range: -3.0125
Max Act: 2.8382. Min Act: -0.1700
Data Index: 5995287 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0125. Min Range: -3.0125
Max Act: 2.8382. Min Act: -0.1700
Data Index: 8581566 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0125. Min Range: -3.0125
Max Act: 2.8223. Min Act: -0.1700
Data Index: 8519752 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0125. Min Range: -3.0125
Max Act: 2.8382. Min Act: -0.1700
Data Index: 2771527 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0125. Min Range: -3.0125
Max Act: 2.8223. Min Act: -0.1700
Data Index: 3880763 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0125. Min Range: -3.0125
Max Act: 2.8223. Min Act: -0.1700
Data Index: 2018597 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0125. Min Range: -3.0125
Max Act: 2.7905. Min Act: -0.1700
Data Index: 3601055 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0125. Min Range: -3.0125
Max Act: 2.7905. Min Act: -0.1700
Data Index: 5641706 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0125. Min Range: -3.0125
Max Act: 2.7905. Min Act: -0.1700
Data Index: 7065267 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0125. Min Range: -3.0125
Max Act: 2.7905. Min Act: -0.1700
Data Index: 6079346 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #19