Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 773 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0007. Min Range: -3.0007
Max Act: 3.0007. Min Act: -0.1700
Data Index: 8185575 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0007. Min Range: -3.0007
Max Act: 3.0007. Min Act: -0.1700
Data Index: 2821822 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0007. Min Range: -3.0007
Max Act: 3.0007. Min Act: -0.1700
Data Index: 8620297 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0007. Min Range: -3.0007
Max Act: 2.9849. Min Act: -0.1700
Data Index: 433591 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0007. Min Range: -3.0007
Max Act: 2.9691. Min Act: -0.1700
Data Index: 1476718 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0007. Min Range: -3.0007
Max Act: 2.9533. Min Act: -0.1700
Data Index: 3124086 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0007. Min Range: -3.0007
Max Act: 2.9374. Min Act: -0.1700
Data Index: 1166456 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0007. Min Range: -3.0007
Max Act: 2.9216. Min Act: -0.1700
Data Index: 3708650 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0007. Min Range: -3.0007
Max Act: 2.9533. Min Act: -0.1700
Data Index: 5605159 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0007. Min Range: -3.0007
Max Act: 2.9216. Min Act: -0.1700
Data Index: 2264569 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0007. Min Range: -3.0007
Max Act: 2.9216. Min Act: -0.1700
Data Index: 7323757 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0007. Min Range: -3.0007
Max Act: 2.9216. Min Act: -0.1700
Data Index: 6216943 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0007. Min Range: -3.0007
Max Act: 2.9057. Min Act: -0.1700
Data Index: 5694330 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0007. Min Range: -3.0007
Max Act: 2.9216. Min Act: -0.1700
Data Index: 5610557 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0007. Min Range: -3.0007
Max Act: 2.9374. Min Act: -0.1700
Data Index: 1905496 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0007. Min Range: -3.0007
Max Act: 2.9057. Min Act: -0.1700
Data Index: 4379813 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0007. Min Range: -3.0007
Max Act: 2.9057. Min Act: -0.1700
Data Index: 947116 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0007. Min Range: -3.0007
Max Act: 2.9216. Min Act: -0.1700
Data Index: 1129407 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0007. Min Range: -3.0007
Max Act: 2.9057. Min Act: -0.1700
Data Index: 5148802 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0007. Min Range: -3.0007
Max Act: 2.8899. Min Act: -0.1700
Data Index: 3724113 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #19