Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1386 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3784. Min Range: -8.3784
Max Act: 8.3784. Min Act: -0.1700
Data Index: 3959057 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3784. Min Range: -8.3784
Max Act: 8.1596. Min Act: -0.1700
Data Index: 7119439 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3784. Min Range: -8.3784
Max Act: 8.1284. Min Act: -0.1700
Data Index: 3785441 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3784. Min Range: -8.3784
Max Act: 8.0346. Min Act: -0.1700
Data Index: 2412767 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3784. Min Range: -8.3784
Max Act: 8.0034. Min Act: -0.1700
Data Index: 7519110 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3784. Min Range: -8.3784
Max Act: 8.0034. Min Act: -0.1700
Data Index: 102878 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3784. Min Range: -8.3784
Max Act: 7.8784. Min Act: -0.1700
Data Index: 8382232 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3784. Min Range: -8.3784
Max Act: 7.9096. Min Act: -0.1700
Data Index: 5075244 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3784. Min Range: -8.3784
Max Act: 7.8471. Min Act: -0.1700
Data Index: 5817193 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3784. Min Range: -8.3784
Max Act: 7.8159. Min Act: -0.1700
Data Index: 3617236 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3784. Min Range: -8.3784
Max Act: 7.7846. Min Act: -0.1700
Data Index: 5534619 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3784. Min Range: -8.3784
Max Act: 7.7846. Min Act: -0.1700
Data Index: 6077405 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3784. Min Range: -8.3784
Max Act: 7.7221. Min Act: -0.1700
Data Index: 3800281 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3784. Min Range: -8.3784
Max Act: 7.7221. Min Act: -0.1700
Data Index: 6013102 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3784. Min Range: -8.3784
Max Act: 7.7221. Min Act: -0.1700
Data Index: 5927052 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3784. Min Range: -8.3784
Max Act: 7.6909. Min Act: -0.1700
Data Index: 7386144 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3784. Min Range: -8.3784
Max Act: 7.6284. Min Act: -0.1700
Data Index: 3380517 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3784. Min Range: -8.3784
Max Act: 7.5971. Min Act: -0.1700
Data Index: 5833912 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3784. Min Range: -8.3784
Max Act: 7.5346. Min Act: -0.1700
Data Index: 6077049 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3784. Min Range: -8.3784
Max Act: 7.5346. Min Act: -0.1700
Data Index: 1904561 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #19