Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3093 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3830. Min Range: -7.3830
Max Act: 7.3830. Min Act: -0.1700
Data Index: 7300146 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3830. Min Range: -7.3830
Max Act: 7.3518. Min Act: -0.1700
Data Index: 5040555 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3830. Min Range: -7.3830
Max Act: 6.9768. Min Act: -0.1700
Data Index: 905250 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3830. Min Range: -7.3830
Max Act: 6.7893. Min Act: -0.1700
Data Index: 1629504 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3830. Min Range: -7.3830
Max Act: 6.8205. Min Act: -0.1700
Data Index: 7066885 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3830. Min Range: -7.3830
Max Act: 6.6955. Min Act: -0.1700
Data Index: 7314506 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3830. Min Range: -7.3830
Max Act: 6.7268. Min Act: -0.1700
Data Index: 2347715 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3830. Min Range: -7.3830
Max Act: 6.7268. Min Act: -0.1700
Data Index: 8744908 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3830. Min Range: -7.3830
Max Act: 6.6330. Min Act: -0.1700
Data Index: 4172383 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3830. Min Range: -7.3830
Max Act: 6.6330. Min Act: -0.1700
Data Index: 4512187 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3830. Min Range: -7.3830
Max Act: 6.6643. Min Act: -0.1700
Data Index: 4555170 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3830. Min Range: -7.3830
Max Act: 6.6330. Min Act: -0.1700
Data Index: 674278 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3830. Min Range: -7.3830
Max Act: 6.6018. Min Act: -0.1700
Data Index: 3903849 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3830. Min Range: -7.3830
Max Act: 6.6018. Min Act: -0.1700
Data Index: 5011073 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3830. Min Range: -7.3830
Max Act: 6.5705. Min Act: -0.1700
Data Index: 5298677 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3830. Min Range: -7.3830
Max Act: 6.6018. Min Act: -0.1700
Data Index: 5878317 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3830. Min Range: -7.3830
Max Act: 6.5393. Min Act: -0.1700
Data Index: 8608889 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3830. Min Range: -7.3830
Max Act: 6.5080. Min Act: -0.1700
Data Index: 1267887 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3830. Min Range: -7.3830
Max Act: 6.5080. Min Act: -0.1700
Data Index: 1168821 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3830. Min Range: -7.3830
Max Act: 6.5080. Min Act: -0.1700
Data Index: 6330856 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #19