Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2121 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7243. Min Range: -5.7243
Max Act: 5.7243. Min Act: -0.1700
Data Index: 5367889 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7243. Min Range: -5.7243
Max Act: 5.7243. Min Act: -0.1700
Data Index: 3454522 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7243. Min Range: -5.7243
Max Act: 5.2868. Min Act: -0.1700
Data Index: 1918786 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7243. Min Range: -5.7243
Max Act: 5.2243. Min Act: -0.1700
Data Index: 7152396 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7243. Min Range: -5.7243
Max Act: 5.1930. Min Act: -0.1700
Data Index: 1640979 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7243. Min Range: -5.7243
Max Act: 5.1618. Min Act: -0.1700
Data Index: 601604 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7243. Min Range: -5.7243
Max Act: 5.1618. Min Act: -0.1700
Data Index: 6406098 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7243. Min Range: -5.7243
Max Act: 5.1305. Min Act: -0.1700
Data Index: 3020094 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7243. Min Range: -5.7243
Max Act: 5.1305. Min Act: -0.1700
Data Index: 4535632 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7243. Min Range: -5.7243
Max Act: 5.1305. Min Act: -0.1700
Data Index: 6213876 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7243. Min Range: -5.7243
Max Act: 5.0680. Min Act: -0.1700
Data Index: 878055 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7243. Min Range: -5.7243
Max Act: 5.0055. Min Act: -0.1700
Data Index: 6478611 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7243. Min Range: -5.7243
Max Act: 5.0055. Min Act: -0.1700
Data Index: 5615622 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7243. Min Range: -5.7243
Max Act: 4.9743. Min Act: -0.1700
Data Index: 8420536 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7243. Min Range: -5.7243
Max Act: 4.9743. Min Act: -0.1700
Data Index: 7531927 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7243. Min Range: -5.7243
Max Act: 4.9743. Min Act: -0.1700
Data Index: 4580399 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7243. Min Range: -5.7243
Max Act: 4.9743. Min Act: -0.1700
Data Index: 1113283 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7243. Min Range: -5.7243
Max Act: 4.9430. Min Act: -0.1700
Data Index: 5930877 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7243. Min Range: -5.7243
Max Act: 4.9430. Min Act: -0.1700
Data Index: 1984486 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7243. Min Range: -5.7243
Max Act: 4.9430. Min Act: -0.1700
Data Index: 3350497 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #19