Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5025 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8522. Min Range: -5.8522
Max Act: 5.8522. Min Act: -0.1700
Data Index: 7520159 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8522. Min Range: -5.8522
Max Act: 5.6959. Min Act: -0.1700
Data Index: 5119138 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8522. Min Range: -5.8522
Max Act: 5.6334. Min Act: -0.1700
Data Index: 3460863 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8522. Min Range: -5.8522
Max Act: 5.6022. Min Act: -0.1700
Data Index: 8081457 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8522. Min Range: -5.8522
Max Act: 5.6334. Min Act: -0.1700
Data Index: 5114777 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8522. Min Range: -5.8522
Max Act: 5.6022. Min Act: -0.1700
Data Index: 872444 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8522. Min Range: -5.8522
Max Act: 5.5709. Min Act: -0.1700
Data Index: 7026103 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8522. Min Range: -5.8522
Max Act: 5.5709. Min Act: -0.1700
Data Index: 1207698 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8522. Min Range: -5.8522
Max Act: 5.5709. Min Act: -0.1700
Data Index: 5846090 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8522. Min Range: -5.8522
Max Act: 5.5397. Min Act: -0.1700
Data Index: 5754946 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8522. Min Range: -5.8522
Max Act: 5.5084. Min Act: -0.1700
Data Index: 7122865 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8522. Min Range: -5.8522
Max Act: 5.4459. Min Act: -0.1700
Data Index: 5300480 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8522. Min Range: -5.8522
Max Act: 5.4772. Min Act: -0.1700
Data Index: 758087 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8522. Min Range: -5.8522
Max Act: 5.5084. Min Act: -0.1700
Data Index: 5846091 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8522. Min Range: -5.8522
Max Act: 5.4459. Min Act: -0.1700
Data Index: 5718662 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8522. Min Range: -5.8522
Max Act: 5.4459. Min Act: -0.1700
Data Index: 7026104 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8522. Min Range: -5.8522
Max Act: 5.4459. Min Act: -0.1700
Data Index: 1550699 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8522. Min Range: -5.8522
Max Act: 5.4147. Min Act: -0.1700
Data Index: 5846092 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8522. Min Range: -5.8522
Max Act: 5.4147. Min Act: -0.1700
Data Index: 941852 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8522. Min Range: -5.8522
Max Act: 5.3834. Min Act: -0.1700
Data Index: 3045995 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #19