Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3019 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1793. Min Range: -3.1793
Max Act: 3.1793. Min Act: -0.1700
Data Index: 6328589 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1793. Min Range: -3.1793
Max Act: 3.1321. Min Act: -0.1700
Data Index: 2816959 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1793. Min Range: -3.1793
Max Act: 3.1321. Min Act: -0.1700
Data Index: 6928270 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1793. Min Range: -3.1793
Max Act: 3.1321. Min Act: -0.1700
Data Index: 2735720 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1793. Min Range: -3.1793
Max Act: 3.1164. Min Act: -0.1700
Data Index: 6799505 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1793. Min Range: -3.1793
Max Act: 3.1006. Min Act: -0.1700
Data Index: 5374455 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1793. Min Range: -3.1793
Max Act: 3.1006. Min Act: -0.1700
Data Index: 1644365 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1793. Min Range: -3.1793
Max Act: 3.1006. Min Act: -0.1700
Data Index: 6799506 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1793. Min Range: -3.1793
Max Act: 3.1006. Min Act: -0.1700
Data Index: 4970558 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1793. Min Range: -3.1793
Max Act: 3.1006. Min Act: -0.1700
Data Index: 96224 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1793. Min Range: -3.1793
Max Act: 3.1164. Min Act: -0.1700
Data Index: 4766500 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1793. Min Range: -3.1793
Max Act: 3.0691. Min Act: -0.1700
Data Index: 6391302 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1793. Min Range: -3.1793
Max Act: 3.0691. Min Act: -0.1700
Data Index: 6630 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1793. Min Range: -3.1793
Max Act: 3.0848. Min Act: -0.1700
Data Index: 1212258 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1793. Min Range: -3.1793
Max Act: 3.0691. Min Act: -0.1700
Data Index: 2880435 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1793. Min Range: -3.1793
Max Act: 3.0533. Min Act: -0.1700
Data Index: 5153214 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1793. Min Range: -3.1793
Max Act: 3.0375. Min Act: -0.1700
Data Index: 2458433 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1793. Min Range: -3.1793
Max Act: 3.0533. Min Act: -0.1700
Data Index: 2982223 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1793. Min Range: -3.1793
Max Act: 3.0375. Min Act: -0.1700
Data Index: 7816777 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1793. Min Range: -3.1793
Max Act: 3.0533. Min Act: -0.1700
Data Index: 3973287 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #19