Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5140 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4814. Min Range: -7.4814
Max Act: 7.4814. Min Act: -0.1700
Data Index: 5570754 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4814. Min Range: -7.4814
Max Act: 7.4814. Min Act: -0.1700
Data Index: 1479982 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4814. Min Range: -7.4814
Max Act: 7.3564. Min Act: -0.1700
Data Index: 8832308 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4814. Min Range: -7.4814
Max Act: 7.3564. Min Act: -0.1700
Data Index: 5117779 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4814. Min Range: -7.4814
Max Act: 7.3564. Min Act: -0.1700
Data Index: 1670780 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4814. Min Range: -7.4814
Max Act: 7.2939. Min Act: -0.1700
Data Index: 607054 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4814. Min Range: -7.4814
Max Act: 7.2939. Min Act: -0.1700
Data Index: 7942815 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4814. Min Range: -7.4814
Max Act: 7.2939. Min Act: -0.1700
Data Index: 2069254 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4814. Min Range: -7.4814
Max Act: 7.2002. Min Act: -0.1700
Data Index: 6053532 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4814. Min Range: -7.4814
Max Act: 7.2002. Min Act: -0.1700
Data Index: 1332150 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4814. Min Range: -7.4814
Max Act: 7.1689. Min Act: -0.1700
Data Index: 3260099 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4814. Min Range: -7.4814
Max Act: 7.1689. Min Act: -0.1700
Data Index: 5034191 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4814. Min Range: -7.4814
Max Act: 7.1689. Min Act: -0.1700
Data Index: 2384429 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4814. Min Range: -7.4814
Max Act: 7.1064. Min Act: -0.1700
Data Index: 3852847 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4814. Min Range: -7.4814
Max Act: 7.1064. Min Act: -0.1700
Data Index: 416832 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4814. Min Range: -7.4814
Max Act: 7.0752. Min Act: -0.1700
Data Index: 1526077 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4814. Min Range: -7.4814
Max Act: 7.0752. Min Act: -0.1700
Data Index: 854533 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4814. Min Range: -7.4814
Max Act: 7.0752. Min Act: -0.1700
Data Index: 210760 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4814. Min Range: -7.4814
Max Act: 7.0752. Min Act: -0.1700
Data Index: 5391770 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4814. Min Range: -7.4814
Max Act: 7.0439. Min Act: -0.1700
Data Index: 2177783 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #19