Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4504 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.2117. Min Range: -2.2117
Max Act: 2.2117. Min Act: -0.1700
Data Index: 5421185 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2117. Min Range: -2.2117
Max Act: 2.1785. Min Act: -0.1700
Data Index: 5192378 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2117. Min Range: -2.2117
Max Act: 2.1619. Min Act: -0.1700
Data Index: 3221058 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2117. Min Range: -2.2117
Max Act: 2.1452. Min Act: -0.1700
Data Index: 4534707 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2117. Min Range: -2.2117
Max Act: 2.1118. Min Act: -0.1700
Data Index: 4896120 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2117. Min Range: -2.2117
Max Act: 2.0951. Min Act: -0.1700
Data Index: 2318933 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2117. Min Range: -2.2117
Max Act: 2.0951. Min Act: -0.1700
Data Index: 3499434 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2117. Min Range: -2.2117
Max Act: 2.0951. Min Act: -0.1700
Data Index: 7935105 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2117. Min Range: -2.2117
Max Act: 2.0951. Min Act: -0.1700
Data Index: 25287 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2117. Min Range: -2.2117
Max Act: 2.1118. Min Act: -0.1700
Data Index: 767674 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2117. Min Range: -2.2117
Max Act: 2.0783. Min Act: -0.1700
Data Index: 2507414 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2117. Min Range: -2.2117
Max Act: 2.0783. Min Act: -0.1700
Data Index: 5523890 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2117. Min Range: -2.2117
Max Act: 2.0783. Min Act: -0.1700
Data Index: 2951370 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2117. Min Range: -2.2117
Max Act: 2.0615. Min Act: -0.1700
Data Index: 6246819 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2117. Min Range: -2.2117
Max Act: 2.0615. Min Act: -0.1700
Data Index: 5373165 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2117. Min Range: -2.2117
Max Act: 2.0447. Min Act: -0.1700
Data Index: 6279185 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2117. Min Range: -2.2117
Max Act: 2.0615. Min Act: -0.1700
Data Index: 4464525 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2117. Min Range: -2.2117
Max Act: 2.0615. Min Act: -0.1700
Data Index: 1834310 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2117. Min Range: -2.2117
Max Act: 2.0615. Min Act: -0.1700
Data Index: 2813377 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2117. Min Range: -2.2117
Max Act: 2.0615. Min Act: -0.1700
Data Index: 2838878 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #19