Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2005 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7226. Min Range: -7.7226
Max Act: 7.7226. Min Act: -0.1700
Data Index: 3938506 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7226. Min Range: -7.7226
Max Act: 7.6289. Min Act: -0.1700
Data Index: 2552181 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7226. Min Range: -7.7226
Max Act: 7.6289. Min Act: -0.1700
Data Index: 3078518 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7226. Min Range: -7.7226
Max Act: 7.5976. Min Act: -0.1700
Data Index: 961012 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7226. Min Range: -7.7226
Max Act: 7.4101. Min Act: -0.1700
Data Index: 5480377 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7226. Min Range: -7.7226
Max Act: 7.4101. Min Act: -0.1700
Data Index: 2088228 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7226. Min Range: -7.7226
Max Act: 7.3789. Min Act: -0.1700
Data Index: 5920828 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7226. Min Range: -7.7226
Max Act: 7.3164. Min Act: -0.1700
Data Index: 5012838 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7226. Min Range: -7.7226
Max Act: 7.2851. Min Act: -0.1700
Data Index: 6616340 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7226. Min Range: -7.7226
Max Act: 7.2851. Min Act: -0.1700
Data Index: 741114 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7226. Min Range: -7.7226
Max Act: 7.2851. Min Act: -0.1700
Data Index: 346076 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7226. Min Range: -7.7226
Max Act: 7.2851. Min Act: -0.1700
Data Index: 8630679 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7226. Min Range: -7.7226
Max Act: 7.2539. Min Act: -0.1700
Data Index: 5752897 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7226. Min Range: -7.7226
Max Act: 7.2226. Min Act: -0.1700
Data Index: 8008735 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7226. Min Range: -7.7226
Max Act: 7.2539. Min Act: -0.1700
Data Index: 5737469 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7226. Min Range: -7.7226
Max Act: 7.1914. Min Act: -0.1700
Data Index: 2304280 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7226. Min Range: -7.7226
Max Act: 7.1914. Min Act: -0.1700
Data Index: 1881895 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7226. Min Range: -7.7226
Max Act: 7.1601. Min Act: -0.1700
Data Index: 2223268 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7226. Min Range: -7.7226
Max Act: 7.1601. Min Act: -0.1700
Data Index: 2484989 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7226. Min Range: -7.7226
Max Act: 7.1601. Min Act: -0.1700
Data Index: 535521 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #19