Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2737 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7564. Min Range: -7.7564
Max Act: 7.7564. Min Act: -0.1700
Data Index: 3309187 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7564. Min Range: -7.7564
Max Act: 7.5689. Min Act: -0.1700
Data Index: 932690 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7564. Min Range: -7.7564
Max Act: 7.3189. Min Act: -0.1700
Data Index: 6910749 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7564. Min Range: -7.7564
Max Act: 7.3189. Min Act: -0.1700
Data Index: 1877420 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7564. Min Range: -7.7564
Max Act: 7.3189. Min Act: -0.1700
Data Index: 3234169 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7564. Min Range: -7.7564
Max Act: 7.2564. Min Act: -0.1700
Data Index: 4024913 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7564. Min Range: -7.7564
Max Act: 7.2564. Min Act: -0.1700
Data Index: 2346738 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7564. Min Range: -7.7564
Max Act: 7.1627. Min Act: -0.1700
Data Index: 5223996 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7564. Min Range: -7.7564
Max Act: 7.1627. Min Act: -0.1700
Data Index: 184500 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7564. Min Range: -7.7564
Max Act: 7.1627. Min Act: -0.1700
Data Index: 6576396 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7564. Min Range: -7.7564
Max Act: 7.1314. Min Act: -0.1700
Data Index: 4064107 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7564. Min Range: -7.7564
Max Act: 7.1314. Min Act: -0.1700
Data Index: 4782859 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7564. Min Range: -7.7564
Max Act: 7.1314. Min Act: -0.1700
Data Index: 7495244 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7564. Min Range: -7.7564
Max Act: 7.1314. Min Act: -0.1700
Data Index: 1560907 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7564. Min Range: -7.7564
Max Act: 7.1002. Min Act: -0.1700
Data Index: 8786445 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7564. Min Range: -7.7564
Max Act: 7.0377. Min Act: -0.1700
Data Index: 4644555 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7564. Min Range: -7.7564
Max Act: 7.0689. Min Act: -0.1700
Data Index: 4245439 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7564. Min Range: -7.7564
Max Act: 7.0377. Min Act: -0.1700
Data Index: 3505097 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7564. Min Range: -7.7564
Max Act: 7.0377. Min Act: -0.1700
Data Index: 6509813 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7564. Min Range: -7.7564
Max Act: 7.0377. Min Act: -0.1700
Data Index: 7792192 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #19