Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4044 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3854. Min Range: -4.3854
Max Act: 4.3854. Min Act: -0.1700
Data Index: 8185359 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3854. Min Range: -4.3854
Max Act: 4.0416. Min Act: -0.1700
Data Index: 3578094 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3854. Min Range: -4.3854
Max Act: 3.9478. Min Act: -0.1700
Data Index: 208437 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3854. Min Range: -4.3854
Max Act: 3.9166. Min Act: -0.1700
Data Index: 4027858 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3854. Min Range: -4.3854
Max Act: 3.9166. Min Act: -0.1700
Data Index: 2278522 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3854. Min Range: -4.3854
Max Act: 3.8540. Min Act: -0.1700
Data Index: 7049733 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3854. Min Range: -4.3854
Max Act: 3.8540. Min Act: -0.1700
Data Index: 8561034 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3854. Min Range: -4.3854
Max Act: 3.8540. Min Act: -0.1700
Data Index: 602991 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3854. Min Range: -4.3854
Max Act: 3.8228. Min Act: -0.1700
Data Index: 6790019 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3854. Min Range: -4.3854
Max Act: 3.8540. Min Act: -0.1700
Data Index: 2756840 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3854. Min Range: -4.3854
Max Act: 3.7915. Min Act: -0.1700
Data Index: 6325529 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3854. Min Range: -4.3854
Max Act: 3.7915. Min Act: -0.1700
Data Index: 5899155 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3854. Min Range: -4.3854
Max Act: 3.7915. Min Act: -0.1700
Data Index: 3508241 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3854. Min Range: -4.3854
Max Act: 3.7602. Min Act: -0.1700
Data Index: 1868774 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3854. Min Range: -4.3854
Max Act: 3.7602. Min Act: -0.1700
Data Index: 4809945 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3854. Min Range: -4.3854
Max Act: 3.7289. Min Act: -0.1700
Data Index: 8059420 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3854. Min Range: -4.3854
Max Act: 3.7602. Min Act: -0.1700
Data Index: 4297701 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3854. Min Range: -4.3854
Max Act: 3.7602. Min Act: -0.1700
Data Index: 7950671 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3854. Min Range: -4.3854
Max Act: 3.7602. Min Act: -0.1700
Data Index: 2690921 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3854. Min Range: -4.3854
Max Act: 3.7289. Min Act: -0.1700
Data Index: 2353439 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #19