Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3171 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8063. Min Range: -5.8063
Max Act: 5.8063. Min Act: -0.1700
Data Index: 959073 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8063. Min Range: -5.8063
Max Act: 5.2126. Min Act: -0.1700
Data Index: 137069 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8063. Min Range: -5.8063
Max Act: 5.0876. Min Act: -0.1700
Data Index: 5603411 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8063. Min Range: -5.8063
Max Act: 5.0876. Min Act: -0.1700
Data Index: 8038635 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8063. Min Range: -5.8063
Max Act: 5.0563. Min Act: -0.1700
Data Index: 4251244 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8063. Min Range: -5.8063
Max Act: 4.9938. Min Act: -0.1700
Data Index: 5133709 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8063. Min Range: -5.8063
Max Act: 5.0251. Min Act: -0.1700
Data Index: 6711434 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8063. Min Range: -5.8063
Max Act: 4.9626. Min Act: -0.1700
Data Index: 7437232 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8063. Min Range: -5.8063
Max Act: 4.9626. Min Act: -0.1700
Data Index: 4508400 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8063. Min Range: -5.8063
Max Act: 4.9313. Min Act: -0.1700
Data Index: 8018249 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8063. Min Range: -5.8063
Max Act: 4.9001. Min Act: -0.1700
Data Index: 4522874 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8063. Min Range: -5.8063
Max Act: 4.8688. Min Act: -0.1700
Data Index: 4388215 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8063. Min Range: -5.8063
Max Act: 4.8376. Min Act: -0.1700
Data Index: 1133126 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8063. Min Range: -5.8063
Max Act: 4.8376. Min Act: -0.1700
Data Index: 8353593 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8063. Min Range: -5.8063
Max Act: 4.8376. Min Act: -0.1700
Data Index: 2109792 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8063. Min Range: -5.8063
Max Act: 4.8376. Min Act: -0.1700
Data Index: 4023400 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8063. Min Range: -5.8063
Max Act: 4.8376. Min Act: -0.1700
Data Index: 2379039 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8063. Min Range: -5.8063
Max Act: 4.8063. Min Act: -0.1700
Data Index: 5106944 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8063. Min Range: -5.8063
Max Act: 4.8063. Min Act: -0.1700
Data Index: 7297731 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8063. Min Range: -5.8063
Max Act: 4.8063. Min Act: -0.1700
Data Index: 4966952 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #19