Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4510 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 13.1040. Min Range: -13.1040
Max Act: 13.1040. Min Act: -0.1700
Data Index: 1266794 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 13.1040. Min Range: -13.1040
Max Act: 12.8540. Min Act: -0.1700
Data Index: 8147547 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 13.1040. Min Range: -13.1040
Max Act: 12.6040. Min Act: -0.1700
Data Index: 8562382 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 13.1040. Min Range: -13.1040
Max Act: 12.6040. Min Act: -0.1700
Data Index: 8631408 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 13.1040. Min Range: -13.1040
Max Act: 12.5415. Min Act: -0.1700
Data Index: 8218719 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 13.1040. Min Range: -13.1040
Max Act: 12.4790. Min Act: -0.1700
Data Index: 7272560 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 13.1040. Min Range: -13.1040
Max Act: 12.3540. Min Act: -0.1700
Data Index: 3416988 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 13.1040. Min Range: -13.1040
Max Act: 12.3540. Min Act: -0.1700
Data Index: 1783358 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 13.1040. Min Range: -13.1040
Max Act: 12.3540. Min Act: -0.1700
Data Index: 1610173 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 13.1040. Min Range: -13.1040
Max Act: 12.1040. Min Act: -0.1700
Data Index: 3839269 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 13.1040. Min Range: -13.1040
Max Act: 12.1040. Min Act: -0.1700
Data Index: 2019609 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 13.1040. Min Range: -13.1040
Max Act: 12.1665. Min Act: -0.1700
Data Index: 2093123 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 13.1040. Min Range: -13.1040
Max Act: 12.0415. Min Act: -0.1700
Data Index: 924594 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 13.1040. Min Range: -13.1040
Max Act: 12.0415. Min Act: -0.1700
Data Index: 195534 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 13.1040. Min Range: -13.1040
Max Act: 12.0415. Min Act: -0.1700
Data Index: 7571422 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 13.1040. Min Range: -13.1040
Max Act: 12.1040. Min Act: -0.1700
Data Index: 6919008 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 13.1040. Min Range: -13.1040
Max Act: 11.9165. Min Act: -0.1700
Data Index: 8518292 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 13.1040. Min Range: -13.1040
Max Act: 11.9790. Min Act: -0.1700
Data Index: 1459916 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 13.1040. Min Range: -13.1040
Max Act: 11.9790. Min Act: -0.1700
Data Index: 6414841 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 13.1040. Min Range: -13.1040
Max Act: 11.9790. Min Act: -0.1700
Data Index: 1651109 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #19