Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4915 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5766. Min Range: -5.5766
Max Act: 5.5766. Min Act: -0.1700
Data Index: 608097 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5766. Min Range: -5.5766
Max Act: 5.5454. Min Act: -0.1700
Data Index: 5851327 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5766. Min Range: -5.5766
Max Act: 5.5454. Min Act: -0.1700
Data Index: 3094765 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5766. Min Range: -5.5766
Max Act: 5.5141. Min Act: -0.1700
Data Index: 2363591 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5766. Min Range: -5.5766
Max Act: 5.4829. Min Act: -0.1700
Data Index: 1963393 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5766. Min Range: -5.5766
Max Act: 5.4829. Min Act: -0.1700
Data Index: 6441302 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5766. Min Range: -5.5766
Max Act: 5.4829. Min Act: -0.1700
Data Index: 3508963 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5766. Min Range: -5.5766
Max Act: 5.4829. Min Act: -0.1700
Data Index: 7670261 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5766. Min Range: -5.5766
Max Act: 5.4516. Min Act: -0.1700
Data Index: 1213569 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5766. Min Range: -5.5766
Max Act: 5.4516. Min Act: -0.1700
Data Index: 6431845 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5766. Min Range: -5.5766
Max Act: 5.4516. Min Act: -0.1700
Data Index: 5549208 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5766. Min Range: -5.5766
Max Act: 5.4516. Min Act: -0.1700
Data Index: 3256668 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5766. Min Range: -5.5766
Max Act: 5.4516. Min Act: -0.1700
Data Index: 4546563 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5766. Min Range: -5.5766
Max Act: 5.4204. Min Act: -0.1700
Data Index: 747035 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5766. Min Range: -5.5766
Max Act: 5.4204. Min Act: -0.1700
Data Index: 5635972 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5766. Min Range: -5.5766
Max Act: 5.4204. Min Act: -0.1700
Data Index: 2068281 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5766. Min Range: -5.5766
Max Act: 5.4204. Min Act: -0.1700
Data Index: 5635867 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5766. Min Range: -5.5766
Max Act: 5.4204. Min Act: -0.1700
Data Index: 3322780 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5766. Min Range: -5.5766
Max Act: 5.4204. Min Act: -0.1700
Data Index: 1717726 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5766. Min Range: -5.5766
Max Act: 5.4204. Min Act: -0.1700
Data Index: 1951682 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #19