Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 733 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8751. Min Range: -4.8751
Max Act: 4.8751. Min Act: -0.1700
Data Index: 7956287 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8751. Min Range: -4.8751
Max Act: 4.8439. Min Act: -0.1700
Data Index: 2652138 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8751. Min Range: -4.8751
Max Act: 4.8439. Min Act: -0.1700
Data Index: 2810462 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8751. Min Range: -4.8751
Max Act: 4.7814. Min Act: -0.1700
Data Index: 3886392 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8751. Min Range: -4.8751
Max Act: 4.7814. Min Act: -0.1700
Data Index: 3948660 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8751. Min Range: -4.8751
Max Act: 4.7814. Min Act: -0.1700
Data Index: 8445779 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8751. Min Range: -4.8751
Max Act: 4.7814. Min Act: -0.1700
Data Index: 332688 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8751. Min Range: -4.8751
Max Act: 4.7814. Min Act: -0.1700
Data Index: 7027159 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8751. Min Range: -4.8751
Max Act: 4.7814. Min Act: -0.1700
Data Index: 7828016 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8751. Min Range: -4.8751
Max Act: 4.7501. Min Act: -0.1700
Data Index: 847672 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8751. Min Range: -4.8751
Max Act: 4.7501. Min Act: -0.1700
Data Index: 7130838 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8751. Min Range: -4.8751
Max Act: 4.7814. Min Act: -0.1700
Data Index: 7585667 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8751. Min Range: -4.8751
Max Act: 4.7501. Min Act: -0.1700
Data Index: 6641175 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8751. Min Range: -4.8751
Max Act: 4.7501. Min Act: -0.1700
Data Index: 1981284 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8751. Min Range: -4.8751
Max Act: 4.7501. Min Act: -0.1700
Data Index: 3159224 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8751. Min Range: -4.8751
Max Act: 4.7189. Min Act: -0.1700
Data Index: 2233728 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8751. Min Range: -4.8751
Max Act: 4.7189. Min Act: -0.1700
Data Index: 4510674 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8751. Min Range: -4.8751
Max Act: 4.7189. Min Act: -0.1700
Data Index: 238201 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8751. Min Range: -4.8751
Max Act: 4.7189. Min Act: -0.1700
Data Index: 6634937 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8751. Min Range: -4.8751
Max Act: 4.7189. Min Act: -0.1700
Data Index: 3047410 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #19