Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2010 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4285. Min Range: -7.4285
Max Act: 7.4285. Min Act: -0.1700
Data Index: 4907370 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4285. Min Range: -7.4285
Max Act: 7.3972. Min Act: -0.1700
Data Index: 75370 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4285. Min Range: -7.4285
Max Act: 7.3035. Min Act: -0.1700
Data Index: 8356016 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4285. Min Range: -7.4285
Max Act: 7.2410. Min Act: -0.1700
Data Index: 2914487 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4285. Min Range: -7.4285
Max Act: 7.1160. Min Act: -0.1700
Data Index: 2515373 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4285. Min Range: -7.4285
Max Act: 7.0222. Min Act: -0.1700
Data Index: 5968153 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4285. Min Range: -7.4285
Max Act: 6.9910. Min Act: -0.1700
Data Index: 2420180 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4285. Min Range: -7.4285
Max Act: 6.9910. Min Act: -0.1700
Data Index: 7942066 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4285. Min Range: -7.4285
Max Act: 6.9597. Min Act: -0.1700
Data Index: 998580 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4285. Min Range: -7.4285
Max Act: 6.8972. Min Act: -0.1700
Data Index: 2148481 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4285. Min Range: -7.4285
Max Act: 6.9285. Min Act: -0.1700
Data Index: 4074236 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4285. Min Range: -7.4285
Max Act: 6.9285. Min Act: -0.1700
Data Index: 2670493 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4285. Min Range: -7.4285
Max Act: 6.8972. Min Act: -0.1700
Data Index: 3538692 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4285. Min Range: -7.4285
Max Act: 6.8660. Min Act: -0.1700
Data Index: 6829377 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4285. Min Range: -7.4285
Max Act: 6.8347. Min Act: -0.1700
Data Index: 26757 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4285. Min Range: -7.4285
Max Act: 6.8347. Min Act: -0.1700
Data Index: 4665816 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4285. Min Range: -7.4285
Max Act: 6.8347. Min Act: -0.1700
Data Index: 5963474 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4285. Min Range: -7.4285
Max Act: 6.8035. Min Act: -0.1700
Data Index: 3389934 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4285. Min Range: -7.4285
Max Act: 6.7722. Min Act: -0.1700
Data Index: 3538684 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4285. Min Range: -7.4285
Max Act: 6.7722. Min Act: -0.1700
Data Index: 7845098 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #19