Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2829 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4494. Min Range: -7.4494
Max Act: 7.4494. Min Act: -0.1700
Data Index: 2910645 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4494. Min Range: -7.4494
Max Act: 7.2619. Min Act: -0.1700
Data Index: 716775 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4494. Min Range: -7.4494
Max Act: 6.9494. Min Act: -0.1700
Data Index: 4254665 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4494. Min Range: -7.4494
Max Act: 6.9494. Min Act: -0.1700
Data Index: 2651336 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4494. Min Range: -7.4494
Max Act: 6.9181. Min Act: -0.1700
Data Index: 7965555 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4494. Min Range: -7.4494
Max Act: 6.8556. Min Act: -0.1700
Data Index: 7412054 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4494. Min Range: -7.4494
Max Act: 6.7931. Min Act: -0.1700
Data Index: 103094 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4494. Min Range: -7.4494
Max Act: 6.7931. Min Act: -0.1700
Data Index: 171152 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4494. Min Range: -7.4494
Max Act: 6.6681. Min Act: -0.1700
Data Index: 4593607 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4494. Min Range: -7.4494
Max Act: 6.6681. Min Act: -0.1700
Data Index: 4068483 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4494. Min Range: -7.4494
Max Act: 6.6681. Min Act: -0.1700
Data Index: 3061414 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4494. Min Range: -7.4494
Max Act: 6.6056. Min Act: -0.1700
Data Index: 7176784 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4494. Min Range: -7.4494
Max Act: 6.6369. Min Act: -0.1700
Data Index: 7632153 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4494. Min Range: -7.4494
Max Act: 6.6369. Min Act: -0.1700
Data Index: 6503263 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4494. Min Range: -7.4494
Max Act: 6.5744. Min Act: -0.1700
Data Index: 7030003 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4494. Min Range: -7.4494
Max Act: 6.5431. Min Act: -0.1700
Data Index: 2941625 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4494. Min Range: -7.4494
Max Act: 6.5431. Min Act: -0.1700
Data Index: 4478567 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4494. Min Range: -7.4494
Max Act: 6.5119. Min Act: -0.1700
Data Index: 2213849 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4494. Min Range: -7.4494
Max Act: 6.4806. Min Act: -0.1700
Data Index: 480742 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4494. Min Range: -7.4494
Max Act: 6.5119. Min Act: -0.1700
Data Index: 3253294 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #19