Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 191 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2846. Min Range: -9.2846
Max Act: 9.2846. Min Act: -0.1700
Data Index: 5050473 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2846. Min Range: -9.2846
Max Act: 9.2221. Min Act: -0.1700
Data Index: 6406346 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2846. Min Range: -9.2846
Max Act: 9.0346. Min Act: -0.1700
Data Index: 7056608 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2846. Min Range: -9.2846
Max Act: 8.9096. Min Act: -0.1700
Data Index: 6843008 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2846. Min Range: -9.2846
Max Act: 8.9096. Min Act: -0.1700
Data Index: 2470005 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2846. Min Range: -9.2846
Max Act: 8.8471. Min Act: -0.1700
Data Index: 5904777 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2846. Min Range: -9.2846
Max Act: 8.8471. Min Act: -0.1700
Data Index: 7934700 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2846. Min Range: -9.2846
Max Act: 8.8471. Min Act: -0.1700
Data Index: 2648119 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2846. Min Range: -9.2846
Max Act: 8.7846. Min Act: -0.1700
Data Index: 8160984 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2846. Min Range: -9.2846
Max Act: 8.7846. Min Act: -0.1700
Data Index: 7310426 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2846. Min Range: -9.2846
Max Act: 8.7846. Min Act: -0.1700
Data Index: 7048324 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2846. Min Range: -9.2846
Max Act: 8.7221. Min Act: -0.1700
Data Index: 4973988 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2846. Min Range: -9.2846
Max Act: 8.7221. Min Act: -0.1700
Data Index: 4136914 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2846. Min Range: -9.2846
Max Act: 8.7221. Min Act: -0.1700
Data Index: 2083203 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2846. Min Range: -9.2846
Max Act: 8.7221. Min Act: -0.1700
Data Index: 1557048 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2846. Min Range: -9.2846
Max Act: 8.7221. Min Act: -0.1700
Data Index: 6652616 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2846. Min Range: -9.2846
Max Act: 8.7221. Min Act: -0.1700
Data Index: 3509761 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2846. Min Range: -9.2846
Max Act: 8.6596. Min Act: -0.1700
Data Index: 570071 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2846. Min Range: -9.2846
Max Act: 8.6596. Min Act: -0.1700
Data Index: 2196024 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2846. Min Range: -9.2846
Max Act: 8.6596. Min Act: -0.1700
Data Index: 3834891 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #19