Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5272 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6011. Min Range: -4.6011
Max Act: 4.6011. Min Act: -0.1700
Data Index: 7057583 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6011. Min Range: -4.6011
Max Act: 4.2573. Min Act: -0.1700
Data Index: 2925931 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6011. Min Range: -4.6011
Max Act: 4.2261. Min Act: -0.1700
Data Index: 6998008 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6011. Min Range: -4.6011
Max Act: 4.2261. Min Act: -0.1700
Data Index: 5970357 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6011. Min Range: -4.6011
Max Act: 4.1948. Min Act: -0.1700
Data Index: 4466072 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6011. Min Range: -4.6011
Max Act: 4.1635. Min Act: -0.1700
Data Index: 3621303 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6011. Min Range: -4.6011
Max Act: 4.1635. Min Act: -0.1700
Data Index: 8451319 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6011. Min Range: -4.6011
Max Act: 4.1323. Min Act: -0.1700
Data Index: 3465656 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6011. Min Range: -4.6011
Max Act: 4.1323. Min Act: -0.1700
Data Index: 1007578 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6011. Min Range: -4.6011
Max Act: 4.1323. Min Act: -0.1700
Data Index: 5225128 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6011. Min Range: -4.6011
Max Act: 4.1635. Min Act: -0.1700
Data Index: 7170995 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6011. Min Range: -4.6011
Max Act: 4.1010. Min Act: -0.1700
Data Index: 5279956 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6011. Min Range: -4.6011
Max Act: 4.1010. Min Act: -0.1700
Data Index: 1855399 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6011. Min Range: -4.6011
Max Act: 4.0698. Min Act: -0.1700
Data Index: 5206594 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6011. Min Range: -4.6011
Max Act: 4.0698. Min Act: -0.1700
Data Index: 2365776 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6011. Min Range: -4.6011
Max Act: 4.0698. Min Act: -0.1700
Data Index: 5220896 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6011. Min Range: -4.6011
Max Act: 4.0385. Min Act: -0.1700
Data Index: 5291344 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6011. Min Range: -4.6011
Max Act: 4.0698. Min Act: -0.1700
Data Index: 705969 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6011. Min Range: -4.6011
Max Act: 4.0698. Min Act: -0.1700
Data Index: 4264968 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6011. Min Range: -4.6011
Max Act: 4.0385. Min Act: -0.1700
Data Index: 5913485 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #19