Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2936 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1597. Min Range: -7.1597
Max Act: 7.1597. Min Act: -0.1700
Data Index: 249910 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1597. Min Range: -7.1597
Max Act: 6.9410. Min Act: -0.1700
Data Index: 6744240 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1597. Min Range: -7.1597
Max Act: 6.7535. Min Act: -0.1700
Data Index: 5312653 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1597. Min Range: -7.1597
Max Act: 6.7222. Min Act: -0.1700
Data Index: 3932459 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1597. Min Range: -7.1597
Max Act: 6.7222. Min Act: -0.1700
Data Index: 378932 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1597. Min Range: -7.1597
Max Act: 6.7222. Min Act: -0.1700
Data Index: 5926370 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1597. Min Range: -7.1597
Max Act: 6.6285. Min Act: -0.1700
Data Index: 14313 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1597. Min Range: -7.1597
Max Act: 6.6285. Min Act: -0.1700
Data Index: 183851 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1597. Min Range: -7.1597
Max Act: 6.6285. Min Act: -0.1700
Data Index: 2259992 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1597. Min Range: -7.1597
Max Act: 6.6285. Min Act: -0.1700
Data Index: 5835767 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1597. Min Range: -7.1597
Max Act: 6.6285. Min Act: -0.1700
Data Index: 4935001 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1597. Min Range: -7.1597
Max Act: 6.6285. Min Act: -0.1700
Data Index: 405174 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1597. Min Range: -7.1597
Max Act: 6.5972. Min Act: -0.1700
Data Index: 5168586 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1597. Min Range: -7.1597
Max Act: 6.5972. Min Act: -0.1700
Data Index: 7030753 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1597. Min Range: -7.1597
Max Act: 6.5660. Min Act: -0.1700
Data Index: 1532790 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1597. Min Range: -7.1597
Max Act: 6.5972. Min Act: -0.1700
Data Index: 4300149 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1597. Min Range: -7.1597
Max Act: 6.5660. Min Act: -0.1700
Data Index: 7536851 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1597. Min Range: -7.1597
Max Act: 6.5035. Min Act: -0.1700
Data Index: 3817006 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1597. Min Range: -7.1597
Max Act: 6.5035. Min Act: -0.1700
Data Index: 2926703 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1597. Min Range: -7.1597
Max Act: 6.5035. Min Act: -0.1700
Data Index: 818515 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #19