Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5991 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7103. Min Range: -8.7103
Max Act: 8.7103. Min Act: -0.1700
Data Index: 3440200 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7103. Min Range: -8.7103
Max Act: 8.3353. Min Act: -0.1700
Data Index: 6658048 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7103. Min Range: -8.7103
Max Act: 8.2728. Min Act: -0.1700
Data Index: 5213205 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7103. Min Range: -8.7103
Max Act: 8.1478. Min Act: -0.1700
Data Index: 7779264 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7103. Min Range: -8.7103
Max Act: 8.0853. Min Act: -0.1700
Data Index: 731831 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7103. Min Range: -8.7103
Max Act: 8.0853. Min Act: -0.1700
Data Index: 2020522 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7103. Min Range: -8.7103
Max Act: 8.0853. Min Act: -0.1700
Data Index: 5813892 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7103. Min Range: -8.7103
Max Act: 8.0853. Min Act: -0.1700
Data Index: 4444018 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7103. Min Range: -8.7103
Max Act: 8.0853. Min Act: -0.1700
Data Index: 348497 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7103. Min Range: -8.7103
Max Act: 8.0853. Min Act: -0.1700
Data Index: 6798505 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7103. Min Range: -8.7103
Max Act: 7.9603. Min Act: -0.1700
Data Index: 6059545 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7103. Min Range: -8.7103
Max Act: 7.9603. Min Act: -0.1700
Data Index: 7117579 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7103. Min Range: -8.7103
Max Act: 7.9603. Min Act: -0.1700
Data Index: 6469945 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7103. Min Range: -8.7103
Max Act: 8.0228. Min Act: -0.1700
Data Index: 2895251 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7103. Min Range: -8.7103
Max Act: 7.9603. Min Act: -0.1700
Data Index: 2434704 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7103. Min Range: -8.7103
Max Act: 7.9603. Min Act: -0.1700
Data Index: 8323257 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7103. Min Range: -8.7103
Max Act: 7.9603. Min Act: -0.1700
Data Index: 2028166 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7103. Min Range: -8.7103
Max Act: 7.9603. Min Act: -0.1700
Data Index: 6249732 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7103. Min Range: -8.7103
Max Act: 7.8978. Min Act: -0.1700
Data Index: 2017425 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7103. Min Range: -8.7103
Max Act: 7.8978. Min Act: -0.1700
Data Index: 3889574 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #19