Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 511 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2933. Min Range: -7.2933
Max Act: 7.2933. Min Act: -0.1700
Data Index: 2238301 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2933. Min Range: -7.2933
Max Act: 7.1058. Min Act: -0.1700
Data Index: 1451186 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2933. Min Range: -7.2933
Max Act: 7.0433. Min Act: -0.1700
Data Index: 7590904 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2933. Min Range: -7.2933
Max Act: 7.0433. Min Act: -0.1700
Data Index: 4962132 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2933. Min Range: -7.2933
Max Act: 6.9183. Min Act: -0.1700
Data Index: 8171029 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2933. Min Range: -7.2933
Max Act: 6.8245. Min Act: -0.1700
Data Index: 1046180 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2933. Min Range: -7.2933
Max Act: 6.8245. Min Act: -0.1700
Data Index: 3866634 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2933. Min Range: -7.2933
Max Act: 6.7933. Min Act: -0.1700
Data Index: 8288275 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2933. Min Range: -7.2933
Max Act: 6.6995. Min Act: -0.1700
Data Index: 4196952 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2933. Min Range: -7.2933
Max Act: 6.6683. Min Act: -0.1700
Data Index: 4283788 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2933. Min Range: -7.2933
Max Act: 6.6683. Min Act: -0.1700
Data Index: 2486581 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2933. Min Range: -7.2933
Max Act: 6.6370. Min Act: -0.1700
Data Index: 3678975 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2933. Min Range: -7.2933
Max Act: 6.6370. Min Act: -0.1700
Data Index: 5789291 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2933. Min Range: -7.2933
Max Act: 6.6058. Min Act: -0.1700
Data Index: 3008071 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2933. Min Range: -7.2933
Max Act: 6.6058. Min Act: -0.1700
Data Index: 2930009 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2933. Min Range: -7.2933
Max Act: 6.6058. Min Act: -0.1700
Data Index: 1925151 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2933. Min Range: -7.2933
Max Act: 6.6058. Min Act: -0.1700
Data Index: 3718752 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2933. Min Range: -7.2933
Max Act: 6.5745. Min Act: -0.1700
Data Index: 4033309 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2933. Min Range: -7.2933
Max Act: 6.5745. Min Act: -0.1700
Data Index: 1017005 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2933. Min Range: -7.2933
Max Act: 6.5433. Min Act: -0.1700
Data Index: 2018254 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #19