Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4351 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0050. Min Range: -5.0050
Max Act: 5.0050. Min Act: -0.1700
Data Index: 6634769 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0050. Min Range: -5.0050
Max Act: 4.9425. Min Act: -0.1700
Data Index: 8129431 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0050. Min Range: -5.0050
Max Act: 4.9113. Min Act: -0.1700
Data Index: 2366693 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0050. Min Range: -5.0050
Max Act: 4.9113. Min Act: -0.1700
Data Index: 3534095 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0050. Min Range: -5.0050
Max Act: 4.9113. Min Act: -0.1700
Data Index: 7637749 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0050. Min Range: -5.0050
Max Act: 4.9113. Min Act: -0.1700
Data Index: 5364691 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0050. Min Range: -5.0050
Max Act: 4.8800. Min Act: -0.1700
Data Index: 4992873 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0050. Min Range: -5.0050
Max Act: 4.8800. Min Act: -0.1700
Data Index: 6668024 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0050. Min Range: -5.0050
Max Act: 4.9113. Min Act: -0.1700
Data Index: 7483697 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0050. Min Range: -5.0050
Max Act: 4.8800. Min Act: -0.1700
Data Index: 4627859 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0050. Min Range: -5.0050
Max Act: 4.8488. Min Act: -0.1700
Data Index: 215990 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0050. Min Range: -5.0050
Max Act: 4.8488. Min Act: -0.1700
Data Index: 4146166 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0050. Min Range: -5.0050
Max Act: 4.8488. Min Act: -0.1700
Data Index: 6687806 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0050. Min Range: -5.0050
Max Act: 4.8488. Min Act: -0.1700
Data Index: 193222 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0050. Min Range: -5.0050
Max Act: 4.8175. Min Act: -0.1700
Data Index: 2012993 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0050. Min Range: -5.0050
Max Act: 4.8488. Min Act: -0.1700
Data Index: 8015645 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0050. Min Range: -5.0050
Max Act: 4.8175. Min Act: -0.1700
Data Index: 3696275 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0050. Min Range: -5.0050
Max Act: 4.8175. Min Act: -0.1700
Data Index: 180437 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0050. Min Range: -5.0050
Max Act: 4.7863. Min Act: -0.1700
Data Index: 2917453 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0050. Min Range: -5.0050
Max Act: 4.8175. Min Act: -0.1700
Data Index: 4017281 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #19