Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3003 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5563. Min Range: -5.5563
Max Act: 5.5563. Min Act: -0.1700
Data Index: 5595843 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5563. Min Range: -5.5563
Max Act: 5.5563. Min Act: -0.1700
Data Index: 3349439 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5563. Min Range: -5.5563
Max Act: 5.5250. Min Act: -0.1700
Data Index: 3032871 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5563. Min Range: -5.5563
Max Act: 5.3688. Min Act: -0.1700
Data Index: 4840718 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5563. Min Range: -5.5563
Max Act: 5.3688. Min Act: -0.1700
Data Index: 8659235 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5563. Min Range: -5.5563
Max Act: 5.3375. Min Act: -0.1700
Data Index: 5172482 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5563. Min Range: -5.5563
Max Act: 5.3063. Min Act: -0.1700
Data Index: 6637680 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5563. Min Range: -5.5563
Max Act: 5.2750. Min Act: -0.1700
Data Index: 6651266 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5563. Min Range: -5.5563
Max Act: 5.2750. Min Act: -0.1700
Data Index: 6018177 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5563. Min Range: -5.5563
Max Act: 5.2438. Min Act: -0.1700
Data Index: 4820031 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5563. Min Range: -5.5563
Max Act: 5.2125. Min Act: -0.1700
Data Index: 1066204 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5563. Min Range: -5.5563
Max Act: 5.1813. Min Act: -0.1700
Data Index: 4914133 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5563. Min Range: -5.5563
Max Act: 5.2125. Min Act: -0.1700
Data Index: 6470082 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5563. Min Range: -5.5563
Max Act: 5.2125. Min Act: -0.1700
Data Index: 8687185 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5563. Min Range: -5.5563
Max Act: 5.1813. Min Act: -0.1700
Data Index: 8643458 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5563. Min Range: -5.5563
Max Act: 5.1813. Min Act: -0.1700
Data Index: 654401 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5563. Min Range: -5.5563
Max Act: 5.1813. Min Act: -0.1700
Data Index: 3588823 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5563. Min Range: -5.5563
Max Act: 5.1813. Min Act: -0.1700
Data Index: 5972748 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5563. Min Range: -5.5563
Max Act: 5.1813. Min Act: -0.1700
Data Index: 7671779 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5563. Min Range: -5.5563
Max Act: 5.1500. Min Act: -0.1700
Data Index: 7945937 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #19