Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3649 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0776. Min Range: -5.0776
Max Act: 5.0776. Min Act: -0.1700
Data Index: 1296530 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0776. Min Range: -5.0776
Max Act: 4.7651. Min Act: -0.1700
Data Index: 2833050 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0776. Min Range: -5.0776
Max Act: 4.7338. Min Act: -0.1700
Data Index: 8643474 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0776. Min Range: -5.0776
Max Act: 4.7338. Min Act: -0.1700
Data Index: 4897414 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0776. Min Range: -5.0776
Max Act: 4.7338. Min Act: -0.1700
Data Index: 1357333 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0776. Min Range: -5.0776
Max Act: 4.7026. Min Act: -0.1700
Data Index: 6251130 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0776. Min Range: -5.0776
Max Act: 4.7026. Min Act: -0.1700
Data Index: 2885823 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0776. Min Range: -5.0776
Max Act: 4.7026. Min Act: -0.1700
Data Index: 7903509 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0776. Min Range: -5.0776
Max Act: 4.7026. Min Act: -0.1700
Data Index: 8345462 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0776. Min Range: -5.0776
Max Act: 4.7026. Min Act: -0.1700
Data Index: 5343608 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0776. Min Range: -5.0776
Max Act: 4.7026. Min Act: -0.1700
Data Index: 3577 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0776. Min Range: -5.0776
Max Act: 4.7026. Min Act: -0.1700
Data Index: 1589781 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0776. Min Range: -5.0776
Max Act: 4.6713. Min Act: -0.1700
Data Index: 2789147 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0776. Min Range: -5.0776
Max Act: 4.6713. Min Act: -0.1700
Data Index: 1554108 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0776. Min Range: -5.0776
Max Act: 4.6713. Min Act: -0.1700
Data Index: 7866096 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0776. Min Range: -5.0776
Max Act: 4.6713. Min Act: -0.1700
Data Index: 7102017 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0776. Min Range: -5.0776
Max Act: 4.6401. Min Act: -0.1700
Data Index: 820631 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0776. Min Range: -5.0776
Max Act: 4.6401. Min Act: -0.1700
Data Index: 2812499 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0776. Min Range: -5.0776
Max Act: 4.6401. Min Act: -0.1700
Data Index: 4811274 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0776. Min Range: -5.0776
Max Act: 4.6401. Min Act: -0.1700
Data Index: 1341484 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #19