Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4867 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8454. Min Range: -5.8454
Max Act: 5.8454. Min Act: -0.1700
Data Index: 6211561 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8454. Min Range: -5.8454
Max Act: 5.8142. Min Act: -0.1700
Data Index: 1180871 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8454. Min Range: -5.8454
Max Act: 5.7829. Min Act: -0.1700
Data Index: 8674132 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8454. Min Range: -5.8454
Max Act: 5.7829. Min Act: -0.1700
Data Index: 2847186 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8454. Min Range: -5.8454
Max Act: 5.6892. Min Act: -0.1700
Data Index: 4072020 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8454. Min Range: -5.8454
Max Act: 5.7204. Min Act: -0.1700
Data Index: 173298 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8454. Min Range: -5.8454
Max Act: 5.6579. Min Act: -0.1700
Data Index: 2154509 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8454. Min Range: -5.8454
Max Act: 5.6579. Min Act: -0.1700
Data Index: 369352 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8454. Min Range: -5.8454
Max Act: 5.6892. Min Act: -0.1700
Data Index: 6547643 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8454. Min Range: -5.8454
Max Act: 5.6579. Min Act: -0.1700
Data Index: 4382583 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8454. Min Range: -5.8454
Max Act: 5.6267. Min Act: -0.1700
Data Index: 4497260 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8454. Min Range: -5.8454
Max Act: 5.5954. Min Act: -0.1700
Data Index: 5234116 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8454. Min Range: -5.8454
Max Act: 5.6267. Min Act: -0.1700
Data Index: 789147 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8454. Min Range: -5.8454
Max Act: 5.5954. Min Act: -0.1700
Data Index: 2412765 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8454. Min Range: -5.8454
Max Act: 5.5954. Min Act: -0.1700
Data Index: 7939207 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8454. Min Range: -5.8454
Max Act: 5.5954. Min Act: -0.1700
Data Index: 2503273 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8454. Min Range: -5.8454
Max Act: 5.5954. Min Act: -0.1700
Data Index: 7887973 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8454. Min Range: -5.8454
Max Act: 5.5954. Min Act: -0.1700
Data Index: 6848801 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8454. Min Range: -5.8454
Max Act: 5.5642. Min Act: -0.1700
Data Index: 4618666 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8454. Min Range: -5.8454
Max Act: 5.6267. Min Act: -0.1700
Data Index: 697911 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #19