Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6368 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9364. Min Range: -4.9364
Max Act: 4.9364. Min Act: -0.1700
Data Index: 441683 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9364. Min Range: -4.9364
Max Act: 4.8114. Min Act: -0.1700
Data Index: 4004435 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9364. Min Range: -4.9364
Max Act: 4.7801. Min Act: -0.1700
Data Index: 8732886 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9364. Min Range: -4.9364
Max Act: 4.7801. Min Act: -0.1700
Data Index: 4747046 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9364. Min Range: -4.9364
Max Act: 4.7489. Min Act: -0.1700
Data Index: 1917670 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9364. Min Range: -4.9364
Max Act: 4.7176. Min Act: -0.1700
Data Index: 598410 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9364. Min Range: -4.9364
Max Act: 4.6864. Min Act: -0.1700
Data Index: 8372828 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9364. Min Range: -4.9364
Max Act: 4.6551. Min Act: -0.1700
Data Index: 6423408 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9364. Min Range: -4.9364
Max Act: 4.6239. Min Act: -0.1700
Data Index: 4246386 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9364. Min Range: -4.9364
Max Act: 4.6551. Min Act: -0.1700
Data Index: 5558939 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9364. Min Range: -4.9364
Max Act: 4.6239. Min Act: -0.1700
Data Index: 424281 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9364. Min Range: -4.9364
Max Act: 4.6239. Min Act: -0.1700
Data Index: 7591892 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9364. Min Range: -4.9364
Max Act: 4.6239. Min Act: -0.1700
Data Index: 6541382 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9364. Min Range: -4.9364
Max Act: 4.6239. Min Act: -0.1700
Data Index: 6065621 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9364. Min Range: -4.9364
Max Act: 4.5926. Min Act: -0.1700
Data Index: 7215649 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9364. Min Range: -4.9364
Max Act: 4.5926. Min Act: -0.1700
Data Index: 1132840 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9364. Min Range: -4.9364
Max Act: 4.5926. Min Act: -0.1700
Data Index: 4780860 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9364. Min Range: -4.9364
Max Act: 4.6239. Min Act: -0.1700
Data Index: 4076973 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9364. Min Range: -4.9364
Max Act: 4.5926. Min Act: -0.1700
Data Index: 5400904 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9364. Min Range: -4.9364
Max Act: 4.5926. Min Act: -0.1700
Data Index: 151011 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #19