Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2823 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8815. Min Range: -3.8815
Max Act: 3.8815. Min Act: -0.1700
Data Index: 1301493 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8815. Min Range: -3.8815
Max Act: 3.8190. Min Act: -0.1700
Data Index: 5217326 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8815. Min Range: -3.8815
Max Act: 3.8190. Min Act: -0.1700
Data Index: 1820018 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8815. Min Range: -3.8815
Max Act: 3.8033. Min Act: -0.1700
Data Index: 3763904 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8815. Min Range: -3.8815
Max Act: 3.7877. Min Act: -0.1700
Data Index: 1464275 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8815. Min Range: -3.8815
Max Act: 3.7251. Min Act: -0.1700
Data Index: 1909107 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8815. Min Range: -3.8815
Max Act: 3.7251. Min Act: -0.1700
Data Index: 7992380 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8815. Min Range: -3.8815
Max Act: 3.6469. Min Act: -0.1700
Data Index: 2373548 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8815. Min Range: -3.8815
Max Act: 3.6313. Min Act: -0.1700
Data Index: 6382851 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8815. Min Range: -3.8815
Max Act: 3.6313. Min Act: -0.1700
Data Index: 8173722 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8815. Min Range: -3.8815
Max Act: 3.6156. Min Act: -0.1700
Data Index: 3636327 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8815. Min Range: -3.8815
Max Act: 3.6156. Min Act: -0.1700
Data Index: 5044989 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8815. Min Range: -3.8815
Max Act: 3.6469. Min Act: -0.1700
Data Index: 8698213 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8815. Min Range: -3.8815
Max Act: 3.6000. Min Act: -0.1700
Data Index: 6680286 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8815. Min Range: -3.8815
Max Act: 3.6000. Min Act: -0.1700
Data Index: 3472835 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8815. Min Range: -3.8815
Max Act: 3.6156. Min Act: -0.1700
Data Index: 3182161 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8815. Min Range: -3.8815
Max Act: 3.5687. Min Act: -0.1700
Data Index: 2657119 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8815. Min Range: -3.8815
Max Act: 3.5687. Min Act: -0.1700
Data Index: 727061 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8815. Min Range: -3.8815
Max Act: 3.5843. Min Act: -0.1700
Data Index: 6427600 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8815. Min Range: -3.8815
Max Act: 3.5843. Min Act: -0.1700
Data Index: 7734677 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #19