Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5788 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5407. Min Range: -7.5407
Max Act: 7.5407. Min Act: -0.1700
Data Index: 7148973 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5407. Min Range: -7.5407
Max Act: 7.5407. Min Act: -0.1700
Data Index: 956833 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5407. Min Range: -7.5407
Max Act: 7.5407. Min Act: -0.1700
Data Index: 3507944 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5407. Min Range: -7.5407
Max Act: 7.4157. Min Act: -0.1700
Data Index: 2950794 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5407. Min Range: -7.5407
Max Act: 7.4157. Min Act: -0.1700
Data Index: 6147794 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5407. Min Range: -7.5407
Max Act: 7.3532. Min Act: -0.1700
Data Index: 1458275 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5407. Min Range: -7.5407
Max Act: 7.3219. Min Act: -0.1700
Data Index: 7444044 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5407. Min Range: -7.5407
Max Act: 7.3219. Min Act: -0.1700
Data Index: 1197746 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5407. Min Range: -7.5407
Max Act: 7.2907. Min Act: -0.1700
Data Index: 1178177 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5407. Min Range: -7.5407
Max Act: 7.1969. Min Act: -0.1700
Data Index: 4067145 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5407. Min Range: -7.5407
Max Act: 7.1969. Min Act: -0.1700
Data Index: 2768820 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5407. Min Range: -7.5407
Max Act: 7.1344. Min Act: -0.1700
Data Index: 2602493 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5407. Min Range: -7.5407
Max Act: 7.1032. Min Act: -0.1700
Data Index: 579604 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5407. Min Range: -7.5407
Max Act: 7.1032. Min Act: -0.1700
Data Index: 2725907 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5407. Min Range: -7.5407
Max Act: 7.0719. Min Act: -0.1700
Data Index: 334151 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5407. Min Range: -7.5407
Max Act: 7.0719. Min Act: -0.1700
Data Index: 6440427 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5407. Min Range: -7.5407
Max Act: 7.0407. Min Act: -0.1700
Data Index: 5607812 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5407. Min Range: -7.5407
Max Act: 7.0407. Min Act: -0.1700
Data Index: 2151439 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5407. Min Range: -7.5407
Max Act: 6.9782. Min Act: -0.1700
Data Index: 5047500 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5407. Min Range: -7.5407
Max Act: 6.9782. Min Act: -0.1700
Data Index: 8116797 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #19