Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2010 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2790. Min Range: -8.2790
Max Act: 8.2790. Min Act: -0.1700
Data Index: 5488027 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2790. Min Range: -8.2790
Max Act: 8.0290. Min Act: -0.1700
Data Index: 6758955 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2790. Min Range: -8.2790
Max Act: 7.9977. Min Act: -0.1700
Data Index: 7320615 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2790. Min Range: -8.2790
Max Act: 7.9665. Min Act: -0.1700
Data Index: 5598511 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2790. Min Range: -8.2790
Max Act: 7.8727. Min Act: -0.1700
Data Index: 5375034 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2790. Min Range: -8.2790
Max Act: 7.8415. Min Act: -0.1700
Data Index: 6181672 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2790. Min Range: -8.2790
Max Act: 7.8102. Min Act: -0.1700
Data Index: 7657095 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2790. Min Range: -8.2790
Max Act: 7.7790. Min Act: -0.1700
Data Index: 5924175 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2790. Min Range: -8.2790
Max Act: 7.7165. Min Act: -0.1700
Data Index: 7762164 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2790. Min Range: -8.2790
Max Act: 7.7477. Min Act: -0.1700
Data Index: 3142424 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2790. Min Range: -8.2790
Max Act: 7.7477. Min Act: -0.1700
Data Index: 1396660 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2790. Min Range: -8.2790
Max Act: 7.7165. Min Act: -0.1700
Data Index: 6957633 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2790. Min Range: -8.2790
Max Act: 7.7165. Min Act: -0.1700
Data Index: 4622708 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2790. Min Range: -8.2790
Max Act: 7.7165. Min Act: -0.1700
Data Index: 8781732 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2790. Min Range: -8.2790
Max Act: 7.7477. Min Act: -0.1700
Data Index: 4505172 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2790. Min Range: -8.2790
Max Act: 7.6852. Min Act: -0.1700
Data Index: 7560929 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2790. Min Range: -8.2790
Max Act: 7.6852. Min Act: -0.1700
Data Index: 4046249 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2790. Min Range: -8.2790
Max Act: 7.6540. Min Act: -0.1700
Data Index: 5537713 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2790. Min Range: -8.2790
Max Act: 7.6227. Min Act: -0.1700
Data Index: 8691406 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2790. Min Range: -8.2790
Max Act: 7.6227. Min Act: -0.1700
Data Index: 114554 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #19