Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2009 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7433. Min Range: -9.7433
Max Act: 9.7433. Min Act: -0.1700
Data Index: 8435378 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7433. Min Range: -9.7433
Max Act: 9.6808. Min Act: -0.1700
Data Index: 7765126 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7433. Min Range: -9.7433
Max Act: 9.6808. Min Act: -0.1700
Data Index: 7803835 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7433. Min Range: -9.7433
Max Act: 9.6183. Min Act: -0.1700
Data Index: 2881521 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7433. Min Range: -9.7433
Max Act: 9.6183. Min Act: -0.1700
Data Index: 290903 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7433. Min Range: -9.7433
Max Act: 9.5558. Min Act: -0.1700
Data Index: 2733642 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7433. Min Range: -9.7433
Max Act: 9.5558. Min Act: -0.1700
Data Index: 5301180 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7433. Min Range: -9.7433
Max Act: 9.5558. Min Act: -0.1700
Data Index: 7496092 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7433. Min Range: -9.7433
Max Act: 9.4933. Min Act: -0.1700
Data Index: 3802949 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7433. Min Range: -9.7433
Max Act: 9.4933. Min Act: -0.1700
Data Index: 8620904 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7433. Min Range: -9.7433
Max Act: 9.4308. Min Act: -0.1700
Data Index: 6406586 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7433. Min Range: -9.7433
Max Act: 9.3683. Min Act: -0.1700
Data Index: 5445364 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7433. Min Range: -9.7433
Max Act: 9.2433. Min Act: -0.1700
Data Index: 7803837 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7433. Min Range: -9.7433
Max Act: 9.3058. Min Act: -0.1700
Data Index: 5445359 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7433. Min Range: -9.7433
Max Act: 9.2433. Min Act: -0.1700
Data Index: 910311 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7433. Min Range: -9.7433
Max Act: 9.2433. Min Act: -0.1700
Data Index: 4346209 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7433. Min Range: -9.7433
Max Act: 9.1808. Min Act: -0.1700
Data Index: 640627 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7433. Min Range: -9.7433
Max Act: 9.1808. Min Act: -0.1700
Data Index: 2532425 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7433. Min Range: -9.7433
Max Act: 9.1808. Min Act: -0.1700
Data Index: 6205738 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7433. Min Range: -9.7433
Max Act: 9.1808. Min Act: -0.1700
Data Index: 2377942 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #19