Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 515 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.6029. Min Range: -10.6029
Max Act: 10.6029. Min Act: -0.1700
Data Index: 3467296 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.6029. Min Range: -10.6029
Max Act: 10.4154. Min Act: -0.1700
Data Index: 2378764 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.6029. Min Range: -10.6029
Max Act: 10.4154. Min Act: -0.1700
Data Index: 1309213 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.6029. Min Range: -10.6029
Max Act: 10.3529. Min Act: -0.1700
Data Index: 7164117 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.6029. Min Range: -10.6029
Max Act: 10.3529. Min Act: -0.1700
Data Index: 4787180 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.6029. Min Range: -10.6029
Max Act: 10.2904. Min Act: -0.1700
Data Index: 8298154 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.6029. Min Range: -10.6029
Max Act: 10.2904. Min Act: -0.1700
Data Index: 1331932 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.6029. Min Range: -10.6029
Max Act: 10.2904. Min Act: -0.1700
Data Index: 3399538 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.6029. Min Range: -10.6029
Max Act: 10.2904. Min Act: -0.1700
Data Index: 4729113 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.6029. Min Range: -10.6029
Max Act: 10.2904. Min Act: -0.1700
Data Index: 2819017 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.6029. Min Range: -10.6029
Max Act: 10.2904. Min Act: -0.1700
Data Index: 3445697 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.6029. Min Range: -10.6029
Max Act: 10.2904. Min Act: -0.1700
Data Index: 5820552 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.6029. Min Range: -10.6029
Max Act: 10.2904. Min Act: -0.1700
Data Index: 5078516 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.6029. Min Range: -10.6029
Max Act: 10.1654. Min Act: -0.1700
Data Index: 2350264 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.6029. Min Range: -10.6029
Max Act: 10.1654. Min Act: -0.1700
Data Index: 6146858 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.6029. Min Range: -10.6029
Max Act: 10.1654. Min Act: -0.1700
Data Index: 2913184 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.6029. Min Range: -10.6029
Max Act: 10.1029. Min Act: -0.1700
Data Index: 3816682 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.6029. Min Range: -10.6029
Max Act: 10.1029. Min Act: -0.1700
Data Index: 4035155 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.6029. Min Range: -10.6029
Max Act: 10.1029. Min Act: -0.1700
Data Index: 3868144 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.6029. Min Range: -10.6029
Max Act: 10.1029. Min Act: -0.1700
Data Index: 1272378 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #19