Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3692 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3827. Min Range: -4.3827
Max Act: 4.3827. Min Act: -0.1700
Data Index: 7528693 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3827. Min Range: -4.3827
Max Act: 4.1951. Min Act: -0.1700
Data Index: 4206274 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3827. Min Range: -4.3827
Max Act: 4.1014. Min Act: -0.1700
Data Index: 6453939 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3827. Min Range: -4.3827
Max Act: 4.0389. Min Act: -0.1700
Data Index: 3428204 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3827. Min Range: -4.3827
Max Act: 3.9763. Min Act: -0.1700
Data Index: 5209785 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3827. Min Range: -4.3827
Max Act: 3.9763. Min Act: -0.1700
Data Index: 767657 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3827. Min Range: -4.3827
Max Act: 3.9763. Min Act: -0.1700
Data Index: 6078653 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3827. Min Range: -4.3827
Max Act: 3.9763. Min Act: -0.1700
Data Index: 7200313 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3827. Min Range: -4.3827
Max Act: 3.9451. Min Act: -0.1700
Data Index: 8552113 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3827. Min Range: -4.3827
Max Act: 3.9451. Min Act: -0.1700
Data Index: 8720974 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3827. Min Range: -4.3827
Max Act: 3.9763. Min Act: -0.1700
Data Index: 4622454 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3827. Min Range: -4.3827
Max Act: 3.9451. Min Act: -0.1700
Data Index: 3197425 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3827. Min Range: -4.3827
Max Act: 3.9294. Min Act: -0.1700
Data Index: 2534055 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3827. Min Range: -4.3827
Max Act: 3.9294. Min Act: -0.1700
Data Index: 759983 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3827. Min Range: -4.3827
Max Act: 3.9138. Min Act: -0.1700
Data Index: 5942741 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3827. Min Range: -4.3827
Max Act: 3.8669. Min Act: -0.1700
Data Index: 6262780 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3827. Min Range: -4.3827
Max Act: 3.8826. Min Act: -0.1700
Data Index: 4702292 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3827. Min Range: -4.3827
Max Act: 3.8826. Min Act: -0.1700
Data Index: 2791908 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3827. Min Range: -4.3827
Max Act: 3.8669. Min Act: -0.1700
Data Index: 8351666 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3827. Min Range: -4.3827
Max Act: 3.8826. Min Act: -0.1700
Data Index: 2488597 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #19