Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1953 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4786. Min Range: -4.4786
Max Act: 4.4786. Min Act: -0.1700
Data Index: 143610 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4786. Min Range: -4.4786
Max Act: 4.3849. Min Act: -0.1700
Data Index: 7628403 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4786. Min Range: -4.4786
Max Act: 4.3849. Min Act: -0.1700
Data Index: 1485978 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4786. Min Range: -4.4786
Max Act: 4.2598. Min Act: -0.1700
Data Index: 638786 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4786. Min Range: -4.4786
Max Act: 4.2286. Min Act: -0.1700
Data Index: 8170105 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4786. Min Range: -4.4786
Max Act: 4.1973. Min Act: -0.1700
Data Index: 1518055 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4786. Min Range: -4.4786
Max Act: 4.1973. Min Act: -0.1700
Data Index: 247330 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4786. Min Range: -4.4786
Max Act: 4.1973. Min Act: -0.1700
Data Index: 5995910 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4786. Min Range: -4.4786
Max Act: 4.1973. Min Act: -0.1700
Data Index: 8281964 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4786. Min Range: -4.4786
Max Act: 4.1661. Min Act: -0.1700
Data Index: 8169593 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4786. Min Range: -4.4786
Max Act: 4.1348. Min Act: -0.1700
Data Index: 4204774 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4786. Min Range: -4.4786
Max Act: 4.1036. Min Act: -0.1700
Data Index: 4962462 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4786. Min Range: -4.4786
Max Act: 4.1348. Min Act: -0.1700
Data Index: 6480148 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4786. Min Range: -4.4786
Max Act: 4.1348. Min Act: -0.1700
Data Index: 2468868 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4786. Min Range: -4.4786
Max Act: 4.0723. Min Act: -0.1700
Data Index: 129529 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4786. Min Range: -4.4786
Max Act: 4.1036. Min Act: -0.1700
Data Index: 4425630 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4786. Min Range: -4.4786
Max Act: 4.0723. Min Act: -0.1700
Data Index: 6371875 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4786. Min Range: -4.4786
Max Act: 4.1036. Min Act: -0.1700
Data Index: 3831393 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4786. Min Range: -4.4786
Max Act: 4.0723. Min Act: -0.1700
Data Index: 6984353 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4786. Min Range: -4.4786
Max Act: 4.0723. Min Act: -0.1700
Data Index: 7142864 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #19