Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3727 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7377. Min Range: -8.7377
Max Act: 8.7377. Min Act: -0.1700
Data Index: 8205764 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7377. Min Range: -8.7377
Max Act: 8.6752. Min Act: -0.1700
Data Index: 2640493 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7377. Min Range: -8.7377
Max Act: 8.6127. Min Act: -0.1700
Data Index: 4605478 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7377. Min Range: -8.7377
Max Act: 8.5502. Min Act: -0.1700
Data Index: 4294593 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7377. Min Range: -8.7377
Max Act: 8.4252. Min Act: -0.1700
Data Index: 489917 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7377. Min Range: -8.7377
Max Act: 8.3627. Min Act: -0.1700
Data Index: 8753228 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7377. Min Range: -8.7377
Max Act: 8.2377. Min Act: -0.1700
Data Index: 8832255 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7377. Min Range: -8.7377
Max Act: 8.1752. Min Act: -0.1700
Data Index: 2951367 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7377. Min Range: -8.7377
Max Act: 8.1752. Min Act: -0.1700
Data Index: 2423027 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7377. Min Range: -8.7377
Max Act: 8.1752. Min Act: -0.1700
Data Index: 5015116 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7377. Min Range: -8.7377
Max Act: 8.1752. Min Act: -0.1700
Data Index: 8397751 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7377. Min Range: -8.7377
Max Act: 8.1127. Min Act: -0.1700
Data Index: 6089221 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7377. Min Range: -8.7377
Max Act: 7.9877. Min Act: -0.1700
Data Index: 8092791 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7377. Min Range: -8.7377
Max Act: 8.0502. Min Act: -0.1700
Data Index: 3967787 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7377. Min Range: -8.7377
Max Act: 8.0502. Min Act: -0.1700
Data Index: 2003727 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7377. Min Range: -8.7377
Max Act: 7.9877. Min Act: -0.1700
Data Index: 2835637 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7377. Min Range: -8.7377
Max Act: 8.0502. Min Act: -0.1700
Data Index: 6422069 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7377. Min Range: -8.7377
Max Act: 8.0502. Min Act: -0.1700
Data Index: 766033 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7377. Min Range: -8.7377
Max Act: 8.0502. Min Act: -0.1700
Data Index: 4180487 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7377. Min Range: -8.7377
Max Act: 7.9877. Min Act: -0.1700
Data Index: 7559576 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #19