Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2836 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0959. Min Range: -7.0959
Max Act: 7.0959. Min Act: -0.1700
Data Index: 4126542 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0959. Min Range: -7.0959
Max Act: 6.7522. Min Act: -0.1700
Data Index: 8061788 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0959. Min Range: -7.0959
Max Act: 6.6584. Min Act: -0.1700
Data Index: 4507336 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0959. Min Range: -7.0959
Max Act: 6.6584. Min Act: -0.1700
Data Index: 1412521 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0959. Min Range: -7.0959
Max Act: 6.5334. Min Act: -0.1700
Data Index: 4481431 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0959. Min Range: -7.0959
Max Act: 6.5334. Min Act: -0.1700
Data Index: 8334227 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0959. Min Range: -7.0959
Max Act: 6.5647. Min Act: -0.1700
Data Index: 7260444 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0959. Min Range: -7.0959
Max Act: 6.5334. Min Act: -0.1700
Data Index: 4126543 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0959. Min Range: -7.0959
Max Act: 6.5022. Min Act: -0.1700
Data Index: 3852757 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0959. Min Range: -7.0959
Max Act: 6.5022. Min Act: -0.1700
Data Index: 2720404 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0959. Min Range: -7.0959
Max Act: 6.4709. Min Act: -0.1700
Data Index: 6944623 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0959. Min Range: -7.0959
Max Act: 6.4709. Min Act: -0.1700
Data Index: 3090311 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0959. Min Range: -7.0959
Max Act: 6.4397. Min Act: -0.1700
Data Index: 67769 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0959. Min Range: -7.0959
Max Act: 6.4084. Min Act: -0.1700
Data Index: 1075376 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0959. Min Range: -7.0959
Max Act: 6.4084. Min Act: -0.1700
Data Index: 6480703 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0959. Min Range: -7.0959
Max Act: 6.3772. Min Act: -0.1700
Data Index: 7299147 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0959. Min Range: -7.0959
Max Act: 6.3459. Min Act: -0.1700
Data Index: 3623814 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0959. Min Range: -7.0959
Max Act: 6.3459. Min Act: -0.1700
Data Index: 8354571 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0959. Min Range: -7.0959
Max Act: 6.3147. Min Act: -0.1700
Data Index: 3395625 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0959. Min Range: -7.0959
Max Act: 6.3459. Min Act: -0.1700
Data Index: 1258812 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #19