Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2061 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9312. Min Range: -6.9312
Max Act: 6.9312. Min Act: -0.1700
Data Index: 2905466 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9312. Min Range: -6.9312
Max Act: 6.9312. Min Act: -0.1700
Data Index: 658810 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9312. Min Range: -6.9312
Max Act: 6.9312. Min Act: -0.1700
Data Index: 3923154 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9312. Min Range: -6.9312
Max Act: 6.8999. Min Act: -0.1700
Data Index: 5278485 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9312. Min Range: -6.9312
Max Act: 6.8687. Min Act: -0.1700
Data Index: 7076958 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9312. Min Range: -6.9312
Max Act: 6.8687. Min Act: -0.1700
Data Index: 6686005 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9312. Min Range: -6.9312
Max Act: 6.8374. Min Act: -0.1700
Data Index: 1810477 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9312. Min Range: -6.9312
Max Act: 6.8374. Min Act: -0.1700
Data Index: 3366721 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9312. Min Range: -6.9312
Max Act: 6.8374. Min Act: -0.1700
Data Index: 440072 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9312. Min Range: -6.9312
Max Act: 6.8062. Min Act: -0.1700
Data Index: 2271908 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9312. Min Range: -6.9312
Max Act: 6.8062. Min Act: -0.1700
Data Index: 2190299 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9312. Min Range: -6.9312
Max Act: 6.7749. Min Act: -0.1700
Data Index: 7993106 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9312. Min Range: -6.9312
Max Act: 6.7749. Min Act: -0.1700
Data Index: 4764125 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9312. Min Range: -6.9312
Max Act: 6.7749. Min Act: -0.1699
Data Index: 2728599 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9312. Min Range: -6.9312
Max Act: 6.8062. Min Act: -0.1700
Data Index: 6624116 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9312. Min Range: -6.9312
Max Act: 6.8062. Min Act: -0.1700
Data Index: 366554 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9312. Min Range: -6.9312
Max Act: 6.7437. Min Act: -0.1700
Data Index: 4068395 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9312. Min Range: -6.9312
Max Act: 6.7437. Min Act: -0.1700
Data Index: 2191547 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9312. Min Range: -6.9312
Max Act: 6.7749. Min Act: -0.1700
Data Index: 5688644 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9312. Min Range: -6.9312
Max Act: 6.7437. Min Act: -0.1700
Data Index: 1116461 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #19