Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2874 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6723. Min Range: -4.6723
Max Act: 4.6723. Min Act: -0.1700
Data Index: 601497 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6723. Min Range: -4.6723
Max Act: 4.6410. Min Act: -0.1700
Data Index: 3704395 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6723. Min Range: -4.6723
Max Act: 4.5785. Min Act: -0.1700
Data Index: 2261253 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6723. Min Range: -4.6723
Max Act: 4.5785. Min Act: -0.1700
Data Index: 7692846 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6723. Min Range: -4.6723
Max Act: 4.5473. Min Act: -0.1700
Data Index: 824448 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6723. Min Range: -4.6723
Max Act: 4.5785. Min Act: -0.1700
Data Index: 1963794 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6723. Min Range: -4.6723
Max Act: 4.5473. Min Act: -0.1700
Data Index: 3704385 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6723. Min Range: -4.6723
Max Act: 4.5160. Min Act: -0.1700
Data Index: 8032307 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6723. Min Range: -4.6723
Max Act: 4.5160. Min Act: -0.1700
Data Index: 7351799 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6723. Min Range: -4.6723
Max Act: 4.4535. Min Act: -0.1700
Data Index: 2703986 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6723. Min Range: -4.6723
Max Act: 4.4848. Min Act: -0.1700
Data Index: 5057969 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6723. Min Range: -4.6723
Max Act: 4.4535. Min Act: -0.1700
Data Index: 718068 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6723. Min Range: -4.6723
Max Act: 4.4535. Min Act: -0.1700
Data Index: 2254447 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6723. Min Range: -4.6723
Max Act: 4.4535. Min Act: -0.1700
Data Index: 2058440 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6723. Min Range: -4.6723
Max Act: 4.4535. Min Act: -0.1700
Data Index: 6505189 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6723. Min Range: -4.6723
Max Act: 4.4223. Min Act: -0.1700
Data Index: 2583735 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6723. Min Range: -4.6723
Max Act: 4.4535. Min Act: -0.1700
Data Index: 3054019 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6723. Min Range: -4.6723
Max Act: 4.4223. Min Act: -0.1700
Data Index: 663272 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6723. Min Range: -4.6723
Max Act: 4.4535. Min Act: -0.1700
Data Index: 6944653 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6723. Min Range: -4.6723
Max Act: 4.3910. Min Act: -0.1700
Data Index: 45558 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #19