Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3578 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2921. Min Range: -6.2921
Max Act: 6.2921. Min Act: -0.1700
Data Index: 7293135 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2921. Min Range: -6.2921
Max Act: 6.2609. Min Act: -0.1700
Data Index: 202580 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2921. Min Range: -6.2921
Max Act: 6.1671. Min Act: -0.1700
Data Index: 2600968 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2921. Min Range: -6.2921
Max Act: 6.0734. Min Act: -0.1700
Data Index: 5136546 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2921. Min Range: -6.2921
Max Act: 6.0421. Min Act: -0.1700
Data Index: 8153069 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2921. Min Range: -6.2921
Max Act: 6.0421. Min Act: -0.1700
Data Index: 7689947 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2921. Min Range: -6.2921
Max Act: 6.0109. Min Act: -0.1700
Data Index: 7293133 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2921. Min Range: -6.2921
Max Act: 6.0109. Min Act: -0.1700
Data Index: 7135338 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2921. Min Range: -6.2921
Max Act: 6.0734. Min Act: -0.1700
Data Index: 3750017 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2921. Min Range: -6.2921
Max Act: 6.0421. Min Act: -0.1700
Data Index: 6865800 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2921. Min Range: -6.2921
Max Act: 6.0421. Min Act: -0.1700
Data Index: 1212745 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2921. Min Range: -6.2921
Max Act: 6.0109. Min Act: -0.1700
Data Index: 6022825 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2921. Min Range: -6.2921
Max Act: 6.0109. Min Act: -0.1700
Data Index: 553374 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2921. Min Range: -6.2921
Max Act: 5.9796. Min Act: -0.1700
Data Index: 7066657 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2921. Min Range: -6.2921
Max Act: 6.0109. Min Act: -0.1700
Data Index: 3536710 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2921. Min Range: -6.2921
Max Act: 6.0109. Min Act: -0.1700
Data Index: 2924369 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2921. Min Range: -6.2921
Max Act: 6.0109. Min Act: -0.1700
Data Index: 435811 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2921. Min Range: -6.2921
Max Act: 5.9796. Min Act: -0.1700
Data Index: 4110141 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2921. Min Range: -6.2921
Max Act: 5.9796. Min Act: -0.1700
Data Index: 4174627 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2921. Min Range: -6.2921
Max Act: 5.9796. Min Act: -0.1700
Data Index: 4636580 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #19