Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3054 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0057. Min Range: -5.0057
Max Act: 5.0057. Min Act: -0.1700
Data Index: 1887881 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0057. Min Range: -5.0057
Max Act: 4.8807. Min Act: -0.1700
Data Index: 990577 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0057. Min Range: -5.0057
Max Act: 4.8495. Min Act: -0.1700
Data Index: 4162362 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0057. Min Range: -5.0057
Max Act: 4.8182. Min Act: -0.1700
Data Index: 8185899 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0057. Min Range: -5.0057
Max Act: 4.8182. Min Act: -0.1700
Data Index: 6024030 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0057. Min Range: -5.0057
Max Act: 4.8182. Min Act: -0.1700
Data Index: 7180982 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0057. Min Range: -5.0057
Max Act: 4.8182. Min Act: -0.1700
Data Index: 1721551 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0057. Min Range: -5.0057
Max Act: 4.7870. Min Act: -0.1700
Data Index: 6613680 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0057. Min Range: -5.0057
Max Act: 4.7870. Min Act: -0.1700
Data Index: 6239396 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0057. Min Range: -5.0057
Max Act: 4.7557. Min Act: -0.1700
Data Index: 2494606 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0057. Min Range: -5.0057
Max Act: 4.7557. Min Act: -0.1700
Data Index: 316127 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0057. Min Range: -5.0057
Max Act: 4.7870. Min Act: -0.1700
Data Index: 8642713 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0057. Min Range: -5.0057
Max Act: 4.7245. Min Act: -0.1700
Data Index: 749670 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0057. Min Range: -5.0057
Max Act: 4.7245. Min Act: -0.1700
Data Index: 3615303 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0057. Min Range: -5.0057
Max Act: 4.7557. Min Act: -0.1700
Data Index: 838941 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0057. Min Range: -5.0057
Max Act: 4.7245. Min Act: -0.1700
Data Index: 3536215 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0057. Min Range: -5.0057
Max Act: 4.7245. Min Act: -0.1700
Data Index: 8289098 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0057. Min Range: -5.0057
Max Act: 4.6620. Min Act: -0.1700
Data Index: 7935047 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0057. Min Range: -5.0057
Max Act: 4.6932. Min Act: -0.1700
Data Index: 3853312 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0057. Min Range: -5.0057
Max Act: 4.6932. Min Act: -0.1700
Data Index: 319760 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #19