Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3931 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4675. Min Range: -7.4675
Max Act: 7.4675. Min Act: -0.1700
Data Index: 5736800 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4675. Min Range: -7.4675
Max Act: 7.2488. Min Act: -0.1700
Data Index: 5870897 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4675. Min Range: -7.4675
Max Act: 7.2800. Min Act: -0.1700
Data Index: 7830499 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4675. Min Range: -7.4675
Max Act: 7.1238. Min Act: -0.1700
Data Index: 2884427 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4675. Min Range: -7.4675
Max Act: 7.1238. Min Act: -0.1700
Data Index: 3613035 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4675. Min Range: -7.4675
Max Act: 7.0300. Min Act: -0.1700
Data Index: 6074905 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4675. Min Range: -7.4675
Max Act: 7.0613. Min Act: -0.1700
Data Index: 4517734 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4675. Min Range: -7.4675
Max Act: 7.0300. Min Act: -0.1700
Data Index: 6120723 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4675. Min Range: -7.4675
Max Act: 6.9363. Min Act: -0.1700
Data Index: 8027893 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4675. Min Range: -7.4675
Max Act: 6.9363. Min Act: -0.1700
Data Index: 1344475 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4675. Min Range: -7.4675
Max Act: 6.9363. Min Act: -0.1700
Data Index: 5071426 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4675. Min Range: -7.4675
Max Act: 6.8425. Min Act: -0.1700
Data Index: 5344679 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4675. Min Range: -7.4675
Max Act: 6.8113. Min Act: -0.1700
Data Index: 4323547 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4675. Min Range: -7.4675
Max Act: 6.8113. Min Act: -0.1700
Data Index: 1129799 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4675. Min Range: -7.4675
Max Act: 6.7800. Min Act: -0.1700
Data Index: 4468243 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4675. Min Range: -7.4675
Max Act: 6.7488. Min Act: -0.1700
Data Index: 2318241 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4675. Min Range: -7.4675
Max Act: 6.7175. Min Act: -0.1700
Data Index: 4429791 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4675. Min Range: -7.4675
Max Act: 6.6863. Min Act: -0.1700
Data Index: 7290772 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4675. Min Range: -7.4675
Max Act: 6.6863. Min Act: -0.1700
Data Index: 5068925 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4675. Min Range: -7.4675
Max Act: 6.6863. Min Act: -0.1700
Data Index: 736370 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #19