Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1548 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3727. Min Range: -8.3727
Max Act: 8.3727. Min Act: -0.1700
Data Index: 479926 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3727. Min Range: -8.3727
Max Act: 7.4977. Min Act: -0.1700
Data Index: 1316691 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3727. Min Range: -8.3727
Max Act: 7.3727. Min Act: -0.1700
Data Index: 1041673 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3727. Min Range: -8.3727
Max Act: 7.3415. Min Act: -0.1700
Data Index: 2200103 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3727. Min Range: -8.3727
Max Act: 7.3102. Min Act: -0.1700
Data Index: 3641944 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3727. Min Range: -8.3727
Max Act: 7.2790. Min Act: -0.1700
Data Index: 5925463 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3727. Min Range: -8.3727
Max Act: 7.1227. Min Act: -0.1700
Data Index: 8143133 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3727. Min Range: -8.3727
Max Act: 7.1227. Min Act: -0.1700
Data Index: 5836844 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3727. Min Range: -8.3727
Max Act: 7.0915. Min Act: -0.1700
Data Index: 4826206 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3727. Min Range: -8.3727
Max Act: 7.0915. Min Act: -0.1700
Data Index: 6289575 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3727. Min Range: -8.3727
Max Act: 7.0602. Min Act: -0.1700
Data Index: 8365108 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3727. Min Range: -8.3727
Max Act: 7.0602. Min Act: -0.1700
Data Index: 6715424 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3727. Min Range: -8.3727
Max Act: 7.0290. Min Act: -0.1700
Data Index: 4635169 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3727. Min Range: -8.3727
Max Act: 6.9665. Min Act: -0.1700
Data Index: 1404158 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3727. Min Range: -8.3727
Max Act: 6.9665. Min Act: -0.1700
Data Index: 5012860 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3727. Min Range: -8.3727
Max Act: 6.9665. Min Act: -0.1700
Data Index: 6331560 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3727. Min Range: -8.3727
Max Act: 6.9665. Min Act: -0.1700
Data Index: 2880541 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3727. Min Range: -8.3727
Max Act: 6.9352. Min Act: -0.1700
Data Index: 2974770 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3727. Min Range: -8.3727
Max Act: 6.9040. Min Act: -0.1700
Data Index: 1275703 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3727. Min Range: -8.3727
Max Act: 6.8415. Min Act: -0.1700
Data Index: 1178417 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #19