Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3360 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2242. Min Range: -6.2242
Max Act: 6.2242. Min Act: -0.1700
Data Index: 5276312 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2242. Min Range: -6.2242
Max Act: 6.0367. Min Act: -0.1700
Data Index: 2232912 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2242. Min Range: -6.2242
Max Act: 5.9742. Min Act: -0.1700
Data Index: 7540699 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2242. Min Range: -6.2242
Max Act: 5.9430. Min Act: -0.1700
Data Index: 4335661 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2242. Min Range: -6.2242
Max Act: 5.9117. Min Act: -0.1700
Data Index: 4369989 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2242. Min Range: -6.2242
Max Act: 5.9117. Min Act: -0.1700
Data Index: 5813609 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2242. Min Range: -6.2242
Max Act: 5.9117. Min Act: -0.1700
Data Index: 1965114 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2242. Min Range: -6.2242
Max Act: 5.8805. Min Act: -0.1700
Data Index: 3158091 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2242. Min Range: -6.2242
Max Act: 5.8492. Min Act: -0.1700
Data Index: 2554784 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2242. Min Range: -6.2242
Max Act: 5.8492. Min Act: -0.1700
Data Index: 6404155 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2242. Min Range: -6.2242
Max Act: 5.8180. Min Act: -0.1700
Data Index: 6692370 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2242. Min Range: -6.2242
Max Act: 5.8492. Min Act: -0.1700
Data Index: 8781896 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2242. Min Range: -6.2242
Max Act: 5.8492. Min Act: -0.1700
Data Index: 2157506 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2242. Min Range: -6.2242
Max Act: 5.8492. Min Act: -0.1700
Data Index: 3094530 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2242. Min Range: -6.2242
Max Act: 5.7867. Min Act: -0.1700
Data Index: 528266 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2242. Min Range: -6.2242
Max Act: 5.8180. Min Act: -0.1700
Data Index: 6527158 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2242. Min Range: -6.2242
Max Act: 5.8180. Min Act: -0.1700
Data Index: 2851087 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2242. Min Range: -6.2242
Max Act: 5.7867. Min Act: -0.1700
Data Index: 5676790 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2242. Min Range: -6.2242
Max Act: 5.7867. Min Act: -0.1700
Data Index: 3348129 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2242. Min Range: -6.2242
Max Act: 5.7867. Min Act: -0.1700
Data Index: 5451192 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #19