Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6300 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6787. Min Range: -8.6787
Max Act: 8.6787. Min Act: -0.1700
Data Index: 7952637 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6787. Min Range: -8.6787
Max Act: 8.4912. Min Act: -0.1700
Data Index: 2716755 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6787. Min Range: -8.6787
Max Act: 8.3037. Min Act: -0.1700
Data Index: 1525513 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6787. Min Range: -8.6787
Max Act: 8.2412. Min Act: -0.1700
Data Index: 3272564 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6787. Min Range: -8.6787
Max Act: 8.2412. Min Act: -0.1700
Data Index: 3526696 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6787. Min Range: -8.6787
Max Act: 8.1787. Min Act: -0.1700
Data Index: 2628394 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6787. Min Range: -8.6787
Max Act: 8.1162. Min Act: -0.1700
Data Index: 2024366 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6787. Min Range: -8.6787
Max Act: 8.0849. Min Act: -0.1700
Data Index: 6595678 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6787. Min Range: -8.6787
Max Act: 8.0224. Min Act: -0.1700
Data Index: 7282846 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6787. Min Range: -8.6787
Max Act: 8.0849. Min Act: -0.1700
Data Index: 8646063 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6787. Min Range: -8.6787
Max Act: 8.0537. Min Act: -0.1700
Data Index: 4998895 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6787. Min Range: -8.6787
Max Act: 8.0224. Min Act: -0.1700
Data Index: 6647372 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6787. Min Range: -8.6787
Max Act: 7.9912. Min Act: -0.1700
Data Index: 4841378 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6787. Min Range: -8.6787
Max Act: 7.9599. Min Act: -0.1700
Data Index: 6883204 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6787. Min Range: -8.6787
Max Act: 7.8974. Min Act: -0.1700
Data Index: 2322203 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6787. Min Range: -8.6787
Max Act: 7.8974. Min Act: -0.1700
Data Index: 5808062 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6787. Min Range: -8.6787
Max Act: 7.8037. Min Act: -0.1700
Data Index: 3156085 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6787. Min Range: -8.6787
Max Act: 7.7724. Min Act: -0.1700
Data Index: 4524605 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6787. Min Range: -8.6787
Max Act: 7.8037. Min Act: -0.1700
Data Index: 1606334 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6787. Min Range: -8.6787
Max Act: 7.7724. Min Act: -0.1700
Data Index: 5097212 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #19