Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2915 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8955. Min Range: -7.8955
Max Act: 7.8955. Min Act: -0.1700
Data Index: 149425 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8955. Min Range: -7.8955
Max Act: 7.8955. Min Act: -0.1700
Data Index: 2902323 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8955. Min Range: -7.8955
Max Act: 7.8955. Min Act: -0.1700
Data Index: 6563516 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8955. Min Range: -7.8955
Max Act: 7.8330. Min Act: -0.1700
Data Index: 8240600 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8955. Min Range: -7.8955
Max Act: 7.8330. Min Act: -0.1700
Data Index: 1696530 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8955. Min Range: -7.8955
Max Act: 7.7080. Min Act: -0.1700
Data Index: 7781731 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8955. Min Range: -7.8955
Max Act: 7.7080. Min Act: -0.1700
Data Index: 2486784 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8955. Min Range: -7.8955
Max Act: 7.6455. Min Act: -0.1700
Data Index: 3006377 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8955. Min Range: -7.8955
Max Act: 7.6143. Min Act: -0.1700
Data Index: 4338375 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8955. Min Range: -7.8955
Max Act: 7.5830. Min Act: -0.1700
Data Index: 687642 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8955. Min Range: -7.8955
Max Act: 7.6143. Min Act: -0.1700
Data Index: 5981676 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8955. Min Range: -7.8955
Max Act: 7.5830. Min Act: -0.1700
Data Index: 5903373 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8955. Min Range: -7.8955
Max Act: 7.4893. Min Act: -0.1700
Data Index: 8628025 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8955. Min Range: -7.8955
Max Act: 7.4580. Min Act: -0.1700
Data Index: 8384498 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8955. Min Range: -7.8955
Max Act: 7.4268. Min Act: -0.1700
Data Index: 2376796 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8955. Min Range: -7.8955
Max Act: 7.3955. Min Act: -0.1700
Data Index: 5182913 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8955. Min Range: -7.8955
Max Act: 7.3955. Min Act: -0.1700
Data Index: 2434634 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8955. Min Range: -7.8955
Max Act: 7.3955. Min Act: -0.1700
Data Index: 8195122 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8955. Min Range: -7.8955
Max Act: 7.3955. Min Act: -0.1700
Data Index: 4839852 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8955. Min Range: -7.8955
Max Act: 7.3955. Min Act: -0.1700
Data Index: 6269339 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #19