Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 561 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.4503. Min Range: -1.4503
Max Act: 1.4503. Min Act: -0.1700
Data Index: 3256114 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4503. Min Range: -1.4503
Max Act: 1.3710. Min Act: -0.1700
Data Index: 6343390 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4503. Min Range: -1.4503
Max Act: 1.3534. Min Act: -0.1700
Data Index: 680060 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4503. Min Range: -1.4503
Max Act: 1.3446. Min Act: -0.1700
Data Index: 7781611 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4503. Min Range: -1.4503
Max Act: 1.3446. Min Act: -0.1697
Data Index: 8530564 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4503. Min Range: -1.4503
Max Act: 1.3534. Min Act: -0.1700
Data Index: 3651482 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4503. Min Range: -1.4503
Max Act: 1.3534. Min Act: -0.1700
Data Index: 567587 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4503. Min Range: -1.4503
Max Act: 1.3446. Min Act: -0.1700
Data Index: 119774 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4503. Min Range: -1.4503
Max Act: 1.3358. Min Act: -0.1700
Data Index: 4095948 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4503. Min Range: -1.4503
Max Act: 1.3446. Min Act: -0.1700
Data Index: 2765720 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4503. Min Range: -1.4503
Max Act: 1.3446. Min Act: -0.1700
Data Index: 8641726 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4503. Min Range: -1.4503
Max Act: 1.3446. Min Act: -0.1700
Data Index: 5278722 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4503. Min Range: -1.4503
Max Act: 1.3446. Min Act: -0.1700
Data Index: 2925130 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4503. Min Range: -1.4503
Max Act: 1.3446. Min Act: -0.1700
Data Index: 8530569 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4503. Min Range: -1.4503
Max Act: 1.3358. Min Act: -0.1700
Data Index: 4814439 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4503. Min Range: -1.4503
Max Act: 1.3270. Min Act: -0.1700
Data Index: 864934 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4503. Min Range: -1.4503
Max Act: 1.3358. Min Act: -0.1700
Data Index: 3098636 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4503. Min Range: -1.4503
Max Act: 1.3270. Min Act: -0.1700
Data Index: 2035319 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4503. Min Range: -1.4503
Max Act: 1.3270. Min Act: -0.1700
Data Index: 2402105 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4503. Min Range: -1.4503
Max Act: 1.3181. Min Act: -0.1700
Data Index: 4760615 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #19