Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1421 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1767. Min Range: -5.1767
Max Act: 5.1767. Min Act: -0.1700
Data Index: 4428833 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1767. Min Range: -5.1767
Max Act: 5.1767. Min Act: -0.1700
Data Index: 1259625 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1767. Min Range: -5.1767
Max Act: 5.1454. Min Act: -0.1700
Data Index: 6359609 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1767. Min Range: -5.1767
Max Act: 5.1142. Min Act: -0.1700
Data Index: 1398046 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1767. Min Range: -5.1767
Max Act: 5.0829. Min Act: -0.1700
Data Index: 2487960 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1767. Min Range: -5.1767
Max Act: 5.0829. Min Act: -0.1700
Data Index: 8561363 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1767. Min Range: -5.1767
Max Act: 5.0517. Min Act: -0.1700
Data Index: 792232 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1767. Min Range: -5.1767
Max Act: 5.0204. Min Act: -0.1700
Data Index: 1259619 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1767. Min Range: -5.1767
Max Act: 4.9579. Min Act: -0.1700
Data Index: 7870000 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1767. Min Range: -5.1767
Max Act: 4.9892. Min Act: -0.1700
Data Index: 1935932 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1767. Min Range: -5.1767
Max Act: 4.9579. Min Act: -0.1700
Data Index: 215246 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1767. Min Range: -5.1767
Max Act: 4.9892. Min Act: -0.1700
Data Index: 162859 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1767. Min Range: -5.1767
Max Act: 4.9267. Min Act: -0.1700
Data Index: 5459583 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1767. Min Range: -5.1767
Max Act: 4.8954. Min Act: -0.1700
Data Index: 1455350 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1767. Min Range: -5.1767
Max Act: 4.9267. Min Act: -0.1700
Data Index: 2187943 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1767. Min Range: -5.1767
Max Act: 4.9267. Min Act: -0.1700
Data Index: 7869986 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1767. Min Range: -5.1767
Max Act: 4.9267. Min Act: -0.1700
Data Index: 1873973 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1767. Min Range: -5.1767
Max Act: 4.8954. Min Act: -0.1700
Data Index: 500247 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1767. Min Range: -5.1767
Max Act: 4.8954. Min Act: -0.1700
Data Index: 4446412 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1767. Min Range: -5.1767
Max Act: 4.8954. Min Act: -0.1700
Data Index: 2566966 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #19