Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3864 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9683. Min Range: -7.9683
Max Act: 7.9683. Min Act: -0.1700
Data Index: 1658841 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9683. Min Range: -7.9683
Max Act: 7.9058. Min Act: -0.1700
Data Index: 6793963 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9683. Min Range: -7.9683
Max Act: 7.8433. Min Act: -0.1700
Data Index: 4961488 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9683. Min Range: -7.9683
Max Act: 7.8433. Min Act: -0.1700
Data Index: 7181037 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9683. Min Range: -7.9683
Max Act: 7.8120. Min Act: -0.1700
Data Index: 5711824 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9683. Min Range: -7.9683
Max Act: 7.7183. Min Act: -0.1700
Data Index: 5363498 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9683. Min Range: -7.9683
Max Act: 7.6558. Min Act: -0.1700
Data Index: 952323 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9683. Min Range: -7.9683
Max Act: 7.6245. Min Act: -0.1700
Data Index: 4759044 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9683. Min Range: -7.9683
Max Act: 7.6245. Min Act: -0.1700
Data Index: 4905801 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9683. Min Range: -7.9683
Max Act: 7.5933. Min Act: -0.1700
Data Index: 843490 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9683. Min Range: -7.9683
Max Act: 7.5933. Min Act: -0.1700
Data Index: 2748931 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9683. Min Range: -7.9683
Max Act: 7.5620. Min Act: -0.1700
Data Index: 2007396 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9683. Min Range: -7.9683
Max Act: 7.4683. Min Act: -0.1700
Data Index: 6162234 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9683. Min Range: -7.9683
Max Act: 7.4995. Min Act: -0.1700
Data Index: 2682412 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9683. Min Range: -7.9683
Max Act: 7.5308. Min Act: -0.1700
Data Index: 3440177 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9683. Min Range: -7.9683
Max Act: 7.4995. Min Act: -0.1700
Data Index: 1480006 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9683. Min Range: -7.9683
Max Act: 7.4683. Min Act: -0.1700
Data Index: 4147601 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9683. Min Range: -7.9683
Max Act: 7.4058. Min Act: -0.1700
Data Index: 1642249 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9683. Min Range: -7.9683
Max Act: 7.3745. Min Act: -0.1700
Data Index: 4821232 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9683. Min Range: -7.9683
Max Act: 7.3745. Min Act: -0.1700
Data Index: 1412570 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #19