Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1095 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3879. Min Range: -9.3879
Max Act: 9.3879. Min Act: -0.1700
Data Index: 613899 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3879. Min Range: -9.3879
Max Act: 9.2629. Min Act: -0.1700
Data Index: 1633985 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3879. Min Range: -9.3879
Max Act: 9.0129. Min Act: -0.1700
Data Index: 7600284 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3879. Min Range: -9.3879
Max Act: 8.7629. Min Act: -0.1700
Data Index: 6811082 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3879. Min Range: -9.3879
Max Act: 8.7629. Min Act: -0.1700
Data Index: 4394724 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3879. Min Range: -9.3879
Max Act: 8.7004. Min Act: -0.1700
Data Index: 3338389 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3879. Min Range: -9.3879
Max Act: 8.7004. Min Act: -0.1700
Data Index: 8550957 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3879. Min Range: -9.3879
Max Act: 8.5754. Min Act: -0.1700
Data Index: 8559172 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3879. Min Range: -9.3879
Max Act: 8.6379. Min Act: -0.1700
Data Index: 5334381 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3879. Min Range: -9.3879
Max Act: 8.5129. Min Act: -0.1700
Data Index: 3877731 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3879. Min Range: -9.3879
Max Act: 8.4504. Min Act: -0.1700
Data Index: 5307642 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3879. Min Range: -9.3879
Max Act: 8.3879. Min Act: -0.1700
Data Index: 5467627 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3879. Min Range: -9.3879
Max Act: 8.3879. Min Act: -0.1700
Data Index: 5651409 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3879. Min Range: -9.3879
Max Act: 8.3254. Min Act: -0.1700
Data Index: 3711950 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3879. Min Range: -9.3879
Max Act: 8.2629. Min Act: -0.1700
Data Index: 2443171 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3879. Min Range: -9.3879
Max Act: 8.2004. Min Act: -0.1700
Data Index: 5576707 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3879. Min Range: -9.3879
Max Act: 8.2004. Min Act: -0.1700
Data Index: 5218382 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3879. Min Range: -9.3879
Max Act: 8.2004. Min Act: -0.1700
Data Index: 4962588 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3879. Min Range: -9.3879
Max Act: 8.2004. Min Act: -0.1700
Data Index: 2927981 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3879. Min Range: -9.3879
Max Act: 8.2004. Min Act: -0.1700
Data Index: 3480885 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #19