Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 899 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1707. Min Range: -3.1707
Max Act: 3.1707. Min Act: -0.1700
Data Index: 1875480 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1707. Min Range: -3.1707
Max Act: 3.1393. Min Act: -0.1700
Data Index: 3594326 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1707. Min Range: -3.1707
Max Act: 3.1393. Min Act: -0.1700
Data Index: 1044554 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1707. Min Range: -3.1707
Max Act: 3.1235. Min Act: -0.1700
Data Index: 4778294 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1707. Min Range: -3.1707
Max Act: 3.1235. Min Act: -0.1700
Data Index: 1017375 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1707. Min Range: -3.1707
Max Act: 3.1078. Min Act: -0.1700
Data Index: 7988139 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1707. Min Range: -3.1707
Max Act: 3.1078. Min Act: -0.1700
Data Index: 6021047 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1707. Min Range: -3.1707
Max Act: 3.0920. Min Act: -0.1700
Data Index: 400172 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1707. Min Range: -3.1707
Max Act: 3.0920. Min Act: -0.1700
Data Index: 4449289 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1707. Min Range: -3.1707
Max Act: 3.0920. Min Act: -0.1700
Data Index: 8025826 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1707. Min Range: -3.1707
Max Act: 3.0920. Min Act: -0.1700
Data Index: 4787362 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1707. Min Range: -3.1707
Max Act: 3.0762. Min Act: -0.1700
Data Index: 6338460 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1707. Min Range: -3.1707
Max Act: 3.0762. Min Act: -0.1700
Data Index: 7464070 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1707. Min Range: -3.1707
Max Act: 3.0762. Min Act: -0.1700
Data Index: 7673504 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1707. Min Range: -3.1707
Max Act: 3.0762. Min Act: -0.1700
Data Index: 1531639 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1707. Min Range: -3.1707
Max Act: 3.0762. Min Act: -0.1700
Data Index: 4984108 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1707. Min Range: -3.1707
Max Act: 3.0762. Min Act: -0.1700
Data Index: 404796 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1707. Min Range: -3.1707
Max Act: 3.0762. Min Act: -0.1700
Data Index: 8128677 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1707. Min Range: -3.1707
Max Act: 3.0762. Min Act: -0.1700
Data Index: 7431806 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1707. Min Range: -3.1707
Max Act: 3.0605. Min Act: -0.1700
Data Index: 3219205 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #19