Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5583 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1832. Min Range: -4.1832
Max Act: 4.1832. Min Act: -0.1700
Data Index: 5498887 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1832. Min Range: -4.1832
Max Act: 3.9644. Min Act: -0.1700
Data Index: 5448383 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1832. Min Range: -4.1832
Max Act: 3.9018. Min Act: -0.1700
Data Index: 984485 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1832. Min Range: -4.1832
Max Act: 3.8393. Min Act: -0.1700
Data Index: 4653604 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1832. Min Range: -4.1832
Max Act: 3.8080. Min Act: -0.1700
Data Index: 5704170 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1832. Min Range: -4.1832
Max Act: 3.7768. Min Act: -0.1700
Data Index: 7446129 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1832. Min Range: -4.1832
Max Act: 3.8080. Min Act: -0.1700
Data Index: 8394462 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1832. Min Range: -4.1832
Max Act: 3.8080. Min Act: -0.1700
Data Index: 7789668 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1832. Min Range: -4.1832
Max Act: 3.8080. Min Act: -0.1700
Data Index: 967300 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1832. Min Range: -4.1832
Max Act: 3.7611. Min Act: -0.1700
Data Index: 1663933 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1832. Min Range: -4.1832
Max Act: 3.7455. Min Act: -0.1700
Data Index: 302439 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1832. Min Range: -4.1832
Max Act: 3.7455. Min Act: -0.1700
Data Index: 1684861 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1832. Min Range: -4.1832
Max Act: 3.7455. Min Act: -0.1700
Data Index: 2927539 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1832. Min Range: -4.1832
Max Act: 3.7298. Min Act: -0.1700
Data Index: 7144478 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1832. Min Range: -4.1832
Max Act: 3.7142. Min Act: -0.1700
Data Index: 8496675 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1832. Min Range: -4.1832
Max Act: 3.6829. Min Act: -0.1700
Data Index: 1610725 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1832. Min Range: -4.1832
Max Act: 3.6986. Min Act: -0.1700
Data Index: 6361711 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1832. Min Range: -4.1832
Max Act: 3.6829. Min Act: -0.1700
Data Index: 6801004 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1832. Min Range: -4.1832
Max Act: 3.6986. Min Act: -0.1700
Data Index: 3008912 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1832. Min Range: -4.1832
Max Act: 3.6829. Min Act: -0.1700
Data Index: 5054495 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #19