Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3486 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0988. Min Range: -7.0988
Max Act: 7.0988. Min Act: -0.1700
Data Index: 7827055 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0988. Min Range: -7.0988
Max Act: 7.0676. Min Act: -0.1700
Data Index: 581731 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0988. Min Range: -7.0988
Max Act: 7.0363. Min Act: -0.1700
Data Index: 5827806 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0988. Min Range: -7.0988
Max Act: 6.9426. Min Act: -0.1700
Data Index: 6262082 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0988. Min Range: -7.0988
Max Act: 6.9113. Min Act: -0.1700
Data Index: 333395 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0988. Min Range: -7.0988
Max Act: 6.9113. Min Act: -0.1700
Data Index: 6087909 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0988. Min Range: -7.0988
Max Act: 6.9113. Min Act: -0.1700
Data Index: 1733903 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0988. Min Range: -7.0988
Max Act: 6.8488. Min Act: -0.1700
Data Index: 2419967 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0988. Min Range: -7.0988
Max Act: 6.7863. Min Act: -0.1700
Data Index: 6049571 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0988. Min Range: -7.0988
Max Act: 6.7863. Min Act: -0.1700
Data Index: 1487367 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0988. Min Range: -7.0988
Max Act: 6.7551. Min Act: -0.1700
Data Index: 8474509 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0988. Min Range: -7.0988
Max Act: 6.7551. Min Act: -0.1700
Data Index: 6236787 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0988. Min Range: -7.0988
Max Act: 6.7238. Min Act: -0.1700
Data Index: 6875767 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0988. Min Range: -7.0988
Max Act: 6.7238. Min Act: -0.1700
Data Index: 6562255 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0988. Min Range: -7.0988
Max Act: 6.6613. Min Act: -0.1700
Data Index: 5997357 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0988. Min Range: -7.0988
Max Act: 6.6613. Min Act: -0.1700
Data Index: 1092624 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0988. Min Range: -7.0988
Max Act: 6.6301. Min Act: -0.1700
Data Index: 1616931 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0988. Min Range: -7.0988
Max Act: 6.5988. Min Act: -0.1700
Data Index: 1188937 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0988. Min Range: -7.0988
Max Act: 6.5988. Min Act: -0.1700
Data Index: 5810000 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0988. Min Range: -7.0988
Max Act: 6.6613. Min Act: -0.1700
Data Index: 6090837 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #19