Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1062 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7223. Min Range: -5.7223
Max Act: 5.7223. Min Act: -0.1700
Data Index: 4317163 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7223. Min Range: -5.7223
Max Act: 5.5973. Min Act: -0.1700
Data Index: 303288 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7223. Min Range: -5.7223
Max Act: 5.4098. Min Act: -0.1700
Data Index: 7175433 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7223. Min Range: -5.7223
Max Act: 5.4098. Min Act: -0.1700
Data Index: 6820712 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7223. Min Range: -5.7223
Max Act: 5.3473. Min Act: -0.1700
Data Index: 2027744 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7223. Min Range: -5.7223
Max Act: 5.2848. Min Act: -0.1700
Data Index: 5468067 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7223. Min Range: -5.7223
Max Act: 5.3160. Min Act: -0.1700
Data Index: 3731352 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7223. Min Range: -5.7223
Max Act: 5.2535. Min Act: -0.1700
Data Index: 2566942 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7223. Min Range: -5.7223
Max Act: 5.2535. Min Act: -0.1700
Data Index: 6052677 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7223. Min Range: -5.7223
Max Act: 5.2535. Min Act: -0.1700
Data Index: 6540083 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7223. Min Range: -5.7223
Max Act: 5.2535. Min Act: -0.1700
Data Index: 1148566 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7223. Min Range: -5.7223
Max Act: 5.2535. Min Act: -0.1700
Data Index: 4756472 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7223. Min Range: -5.7223
Max Act: 5.2223. Min Act: -0.1700
Data Index: 5490601 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7223. Min Range: -5.7223
Max Act: 5.2223. Min Act: -0.1700
Data Index: 7798703 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7223. Min Range: -5.7223
Max Act: 5.2223. Min Act: -0.1700
Data Index: 5196136 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7223. Min Range: -5.7223
Max Act: 5.2535. Min Act: -0.1700
Data Index: 228698 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7223. Min Range: -5.7223
Max Act: 5.2223. Min Act: -0.1700
Data Index: 5996412 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7223. Min Range: -5.7223
Max Act: 5.2223. Min Act: -0.1700
Data Index: 5702590 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7223. Min Range: -5.7223
Max Act: 5.1910. Min Act: -0.1700
Data Index: 758625 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7223. Min Range: -5.7223
Max Act: 5.1910. Min Act: -0.1700
Data Index: 531044 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #19