Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2518 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.9093. Min Range: -5.9093
Max Act: 5.9093. Min Act: -0.1700
Data Index: 633136 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9093. Min Range: -5.9093
Max Act: 5.8156. Min Act: -0.1700
Data Index: 7045288 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9093. Min Range: -5.9093
Max Act: 5.8156. Min Act: -0.1700
Data Index: 1611201 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9093. Min Range: -5.9093
Max Act: 5.7531. Min Act: -0.1700
Data Index: 6120869 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9093. Min Range: -5.9093
Max Act: 5.6906. Min Act: -0.1700
Data Index: 1894694 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9093. Min Range: -5.9093
Max Act: 5.6906. Min Act: -0.1700
Data Index: 4504722 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9093. Min Range: -5.9093
Max Act: 5.6593. Min Act: -0.1700
Data Index: 7430687 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9093. Min Range: -5.9093
Max Act: 5.6593. Min Act: -0.1700
Data Index: 5840911 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9093. Min Range: -5.9093
Max Act: 5.5656. Min Act: -0.1700
Data Index: 1836634 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9093. Min Range: -5.9093
Max Act: 5.5031. Min Act: -0.1700
Data Index: 3881552 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9093. Min Range: -5.9093
Max Act: 5.5031. Min Act: -0.1700
Data Index: 3427851 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9093. Min Range: -5.9093
Max Act: 5.5031. Min Act: -0.1700
Data Index: 5890784 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9093. Min Range: -5.9093
Max Act: 5.4718. Min Act: -0.1700
Data Index: 7396672 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9093. Min Range: -5.9093
Max Act: 5.4718. Min Act: -0.1700
Data Index: 2074619 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9093. Min Range: -5.9093
Max Act: 5.4718. Min Act: -0.1700
Data Index: 4980585 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9093. Min Range: -5.9093
Max Act: 5.4093. Min Act: -0.1700
Data Index: 7366096 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9093. Min Range: -5.9093
Max Act: 5.4093. Min Act: -0.1700
Data Index: 6041221 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9093. Min Range: -5.9093
Max Act: 5.4093. Min Act: -0.1700
Data Index: 3393464 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9093. Min Range: -5.9093
Max Act: 5.3781. Min Act: -0.1700
Data Index: 6950882 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9093. Min Range: -5.9093
Max Act: 5.3468. Min Act: -0.1700
Data Index: 4490834 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #19