Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3513 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8882. Min Range: -5.8882
Max Act: 5.8882. Min Act: -0.1700
Data Index: 2404576 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8882. Min Range: -5.8882
Max Act: 5.8257. Min Act: -0.1700
Data Index: 1692910 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8882. Min Range: -5.8882
Max Act: 5.7945. Min Act: -0.1700
Data Index: 7695416 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8882. Min Range: -5.8882
Max Act: 5.7945. Min Act: -0.1700
Data Index: 1647754 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8882. Min Range: -5.8882
Max Act: 5.7632. Min Act: -0.1700
Data Index: 2919526 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8882. Min Range: -5.8882
Max Act: 5.7632. Min Act: -0.1700
Data Index: 1474593 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8882. Min Range: -5.8882
Max Act: 5.7632. Min Act: -0.1700
Data Index: 1836656 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8882. Min Range: -5.8882
Max Act: 5.7320. Min Act: -0.1700
Data Index: 1647755 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8882. Min Range: -5.8882
Max Act: 5.7320. Min Act: -0.1699
Data Index: 6745843 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8882. Min Range: -5.8882
Max Act: 5.7320. Min Act: -0.1700
Data Index: 787927 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8882. Min Range: -5.8882
Max Act: 5.7007. Min Act: -0.1700
Data Index: 1764667 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8882. Min Range: -5.8882
Max Act: 5.7320. Min Act: -0.1700
Data Index: 4118319 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8882. Min Range: -5.8882
Max Act: 5.7007. Min Act: -0.1700
Data Index: 6486292 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8882. Min Range: -5.8882
Max Act: 5.7007. Min Act: -0.1700
Data Index: 1362076 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8882. Min Range: -5.8882
Max Act: 5.7007. Min Act: -0.1700
Data Index: 2963683 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8882. Min Range: -5.8882
Max Act: 5.7007. Min Act: -0.1700
Data Index: 1763766 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8882. Min Range: -5.8882
Max Act: 5.7007. Min Act: -0.1700
Data Index: 6537245 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8882. Min Range: -5.8882
Max Act: 5.7007. Min Act: -0.1700
Data Index: 2870338 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8882. Min Range: -5.8882
Max Act: 5.7007. Min Act: -0.1700
Data Index: 106685 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8882. Min Range: -5.8882
Max Act: 5.7007. Min Act: -0.1700
Data Index: 2163075 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #19