Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2052 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.9941. Min Range: -8.9941
Max Act: 8.9941. Min Act: -0.1700
Data Index: 7043024 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9941. Min Range: -8.9941
Max Act: 8.8691. Min Act: -0.1700
Data Index: 1759463 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9941. Min Range: -8.9941
Max Act: 8.8066. Min Act: -0.1700
Data Index: 4632171 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9941. Min Range: -8.9941
Max Act: 8.8066. Min Act: -0.1700
Data Index: 30150 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9941. Min Range: -8.9941
Max Act: 8.7441. Min Act: -0.1700
Data Index: 4432344 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9941. Min Range: -8.9941
Max Act: 8.7441. Min Act: -0.1700
Data Index: 7795785 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9941. Min Range: -8.9941
Max Act: 8.8066. Min Act: -0.1700
Data Index: 5473219 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9941. Min Range: -8.9941
Max Act: 8.7441. Min Act: -0.1700
Data Index: 1314877 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9941. Min Range: -8.9941
Max Act: 8.7441. Min Act: -0.1700
Data Index: 7726304 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9941. Min Range: -8.9941
Max Act: 8.6816. Min Act: -0.1700
Data Index: 4707333 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9941. Min Range: -8.9941
Max Act: 8.6816. Min Act: -0.1700
Data Index: 2022775 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9941. Min Range: -8.9941
Max Act: 8.6191. Min Act: -0.1700
Data Index: 7464423 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9941. Min Range: -8.9941
Max Act: 8.6816. Min Act: -0.1700
Data Index: 5551014 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9941. Min Range: -8.9941
Max Act: 8.6191. Min Act: -0.1700
Data Index: 6526601 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9941. Min Range: -8.9941
Max Act: 8.5566. Min Act: -0.1700
Data Index: 651900 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9941. Min Range: -8.9941
Max Act: 8.5566. Min Act: -0.1700
Data Index: 3693892 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9941. Min Range: -8.9941
Max Act: 8.4941. Min Act: -0.1700
Data Index: 1341777 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9941. Min Range: -8.9941
Max Act: 8.6191. Min Act: -0.1700
Data Index: 5672060 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9941. Min Range: -8.9941
Max Act: 8.5566. Min Act: -0.1700
Data Index: 920333 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9941. Min Range: -8.9941
Max Act: 8.4941. Min Act: -0.1700
Data Index: 7062096 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #19