Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1246 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.1705. Min Range: -10.1705
Max Act: 10.1705. Min Act: -0.1700
Data Index: 3420015 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.1705. Min Range: -10.1705
Max Act: 9.9205. Min Act: -0.1700
Data Index: 1387406 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.1705. Min Range: -10.1705
Max Act: 9.5455. Min Act: -0.1700
Data Index: 4261162 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.1705. Min Range: -10.1705
Max Act: 9.5455. Min Act: -0.1700
Data Index: 6564833 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.1705. Min Range: -10.1705
Max Act: 9.4205. Min Act: -0.1700
Data Index: 8297053 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.1705. Min Range: -10.1705
Max Act: 9.2955. Min Act: -0.1700
Data Index: 6591704 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.1705. Min Range: -10.1705
Max Act: 9.2330. Min Act: -0.1700
Data Index: 2030858 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.1705. Min Range: -10.1705
Max Act: 9.1080. Min Act: -0.1700
Data Index: 4150023 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.1705. Min Range: -10.1705
Max Act: 9.1080. Min Act: -0.1700
Data Index: 88404 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.1705. Min Range: -10.1705
Max Act: 9.0455. Min Act: -0.1700
Data Index: 1368148 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.1705. Min Range: -10.1705
Max Act: 9.0455. Min Act: -0.1700
Data Index: 3378399 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.1705. Min Range: -10.1705
Max Act: 9.0455. Min Act: -0.1700
Data Index: 4699184 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.1705. Min Range: -10.1705
Max Act: 9.0455. Min Act: -0.1700
Data Index: 4635240 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.1705. Min Range: -10.1705
Max Act: 9.0455. Min Act: -0.1700
Data Index: 2561877 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.1705. Min Range: -10.1705
Max Act: 9.0455. Min Act: -0.1700
Data Index: 6564839 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.1705. Min Range: -10.1705
Max Act: 8.9830. Min Act: -0.1700
Data Index: 6247081 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.1705. Min Range: -10.1705
Max Act: 8.9830. Min Act: -0.1700
Data Index: 8252004 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.1705. Min Range: -10.1705
Max Act: 8.9205. Min Act: -0.1700
Data Index: 1813997 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.1705. Min Range: -10.1705
Max Act: 8.9205. Min Act: -0.1700
Data Index: 1136352 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.1705. Min Range: -10.1705
Max Act: 8.9205. Min Act: -0.1700
Data Index: 7929334 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #19