Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4650 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8343. Min Range: -7.8343
Max Act: 7.8343. Min Act: -0.1700
Data Index: 364238 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8343. Min Range: -7.8343
Max Act: 7.7093. Min Act: -0.1700
Data Index: 73892 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8343. Min Range: -7.8343
Max Act: 7.7093. Min Act: -0.1700
Data Index: 6135613 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8343. Min Range: -7.8343
Max Act: 7.7093. Min Act: -0.1700
Data Index: 1421129 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8343. Min Range: -7.8343
Max Act: 7.6468. Min Act: -0.1700
Data Index: 1394628 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8343. Min Range: -7.8343
Max Act: 7.4905. Min Act: -0.1700
Data Index: 6973705 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8343. Min Range: -7.8343
Max Act: 7.3968. Min Act: -0.1700
Data Index: 2164194 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8343. Min Range: -7.8343
Max Act: 7.3968. Min Act: -0.1700
Data Index: 7308256 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8343. Min Range: -7.8343
Max Act: 7.3968. Min Act: -0.1700
Data Index: 8498902 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8343. Min Range: -7.8343
Max Act: 7.3968. Min Act: -0.1700
Data Index: 457844 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8343. Min Range: -7.8343
Max Act: 7.3655. Min Act: -0.1700
Data Index: 2421726 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8343. Min Range: -7.8343
Max Act: 7.3655. Min Act: -0.1700
Data Index: 7547692 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8343. Min Range: -7.8343
Max Act: 7.3343. Min Act: -0.1700
Data Index: 2843792 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8343. Min Range: -7.8343
Max Act: 7.3343. Min Act: -0.1700
Data Index: 6855344 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8343. Min Range: -7.8343
Max Act: 7.3343. Min Act: -0.1700
Data Index: 8131234 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8343. Min Range: -7.8343
Max Act: 7.3030. Min Act: -0.1700
Data Index: 707028 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8343. Min Range: -7.8343
Max Act: 7.3030. Min Act: -0.1700
Data Index: 1007231 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8343. Min Range: -7.8343
Max Act: 7.3030. Min Act: -0.1700
Data Index: 457217 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8343. Min Range: -7.8343
Max Act: 7.2718. Min Act: -0.1700
Data Index: 1906787 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8343. Min Range: -7.8343
Max Act: 7.2718. Min Act: -0.1700
Data Index: 1352920 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #19