Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4653 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2815. Min Range: -5.2815
Max Act: 5.2815. Min Act: -0.1700
Data Index: 3637574 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2815. Min Range: -5.2815
Max Act: 5.0940. Min Act: -0.1700
Data Index: 7044685 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2815. Min Range: -5.2815
Max Act: 4.9690. Min Act: -0.1700
Data Index: 2951658 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2815. Min Range: -5.2815
Max Act: 4.9065. Min Act: -0.1700
Data Index: 7939947 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2815. Min Range: -5.2815
Max Act: 4.8440. Min Act: -0.1700
Data Index: 3795858 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2815. Min Range: -5.2815
Max Act: 4.8440. Min Act: -0.1700
Data Index: 5278005 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2815. Min Range: -5.2815
Max Act: 4.8440. Min Act: -0.1700
Data Index: 5455400 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2815. Min Range: -5.2815
Max Act: 4.7503. Min Act: -0.1700
Data Index: 3902651 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2815. Min Range: -5.2815
Max Act: 4.7815. Min Act: -0.1700
Data Index: 4616774 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2815. Min Range: -5.2815
Max Act: 4.7190. Min Act: -0.1700
Data Index: 7066902 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2815. Min Range: -5.2815
Max Act: 4.7190. Min Act: -0.1700
Data Index: 4265476 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2815. Min Range: -5.2815
Max Act: 4.7190. Min Act: -0.1700
Data Index: 584132 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2815. Min Range: -5.2815
Max Act: 4.7503. Min Act: -0.1700
Data Index: 5116683 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2815. Min Range: -5.2815
Max Act: 4.6565. Min Act: -0.1700
Data Index: 5304276 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2815. Min Range: -5.2815
Max Act: 4.6565. Min Act: -0.1700
Data Index: 1046986 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2815. Min Range: -5.2815
Max Act: 4.6565. Min Act: -0.1700
Data Index: 5099432 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2815. Min Range: -5.2815
Max Act: 4.6878. Min Act: -0.1700
Data Index: 5851419 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2815. Min Range: -5.2815
Max Act: 4.6253. Min Act: -0.1700
Data Index: 4116842 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2815. Min Range: -5.2815
Max Act: 4.6253. Min Act: -0.1700
Data Index: 3145117 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2815. Min Range: -5.2815
Max Act: 4.5940. Min Act: -0.1700
Data Index: 961147 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #19