Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4880 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3176. Min Range: -9.3176
Max Act: 9.3176. Min Act: -0.1700
Data Index: 6448580 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3176. Min Range: -9.3176
Max Act: 9.1926. Min Act: -0.1700
Data Index: 2194012 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3176. Min Range: -9.3176
Max Act: 9.0676. Min Act: -0.1700
Data Index: 935800 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3176. Min Range: -9.3176
Max Act: 9.0051. Min Act: -0.1700
Data Index: 2547412 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3176. Min Range: -9.3176
Max Act: 9.0676. Min Act: -0.1700
Data Index: 48907 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3176. Min Range: -9.3176
Max Act: 8.9426. Min Act: -0.1700
Data Index: 6605748 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3176. Min Range: -9.3176
Max Act: 9.0051. Min Act: -0.1700
Data Index: 2561981 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3176. Min Range: -9.3176
Max Act: 8.8801. Min Act: -0.1700
Data Index: 7901075 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3176. Min Range: -9.3176
Max Act: 8.8801. Min Act: -0.1700
Data Index: 8248710 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3176. Min Range: -9.3176
Max Act: 8.8176. Min Act: -0.1700
Data Index: 5484127 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3176. Min Range: -9.3176
Max Act: 8.8801. Min Act: -0.1700
Data Index: 4220541 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3176. Min Range: -9.3176
Max Act: 8.8801. Min Act: -0.1700
Data Index: 7317786 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3176. Min Range: -9.3176
Max Act: 8.8801. Min Act: -0.1700
Data Index: 5377736 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3176. Min Range: -9.3176
Max Act: 8.8801. Min Act: -0.1700
Data Index: 1669894 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3176. Min Range: -9.3176
Max Act: 8.8801. Min Act: -0.1700
Data Index: 6697670 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3176. Min Range: -9.3176
Max Act: 8.8801. Min Act: -0.1700
Data Index: 5464338 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3176. Min Range: -9.3176
Max Act: 8.8801. Min Act: -0.1700
Data Index: 7143026 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3176. Min Range: -9.3176
Max Act: 8.8176. Min Act: -0.1700
Data Index: 3500346 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3176. Min Range: -9.3176
Max Act: 8.7551. Min Act: -0.1700
Data Index: 920049 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3176. Min Range: -9.3176
Max Act: 8.7551. Min Act: -0.1700
Data Index: 752186 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #19