Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5906 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4346. Min Range: -5.4346
Max Act: 5.4346. Min Act: -0.1700
Data Index: 8776308 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4346. Min Range: -5.4346
Max Act: 5.3721. Min Act: -0.1700
Data Index: 6124745 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4346. Min Range: -5.4346
Max Act: 5.3721. Min Act: -0.1700
Data Index: 3413292 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4346. Min Range: -5.4346
Max Act: 5.2471. Min Act: -0.1700
Data Index: 7381107 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4346. Min Range: -5.4346
Max Act: 5.2471. Min Act: -0.1700
Data Index: 7210641 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4346. Min Range: -5.4346
Max Act: 5.2158. Min Act: -0.1700
Data Index: 2930084 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4346. Min Range: -5.4346
Max Act: 5.2158. Min Act: -0.1700
Data Index: 3379855 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4346. Min Range: -5.4346
Max Act: 5.1846. Min Act: -0.1700
Data Index: 383736 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4346. Min Range: -5.4346
Max Act: 5.1846. Min Act: -0.1700
Data Index: 2587607 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4346. Min Range: -5.4346
Max Act: 5.1846. Min Act: -0.1700
Data Index: 4360337 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4346. Min Range: -5.4346
Max Act: 5.1533. Min Act: -0.1700
Data Index: 7496411 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4346. Min Range: -5.4346
Max Act: 5.1846. Min Act: -0.1700
Data Index: 4475000 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4346. Min Range: -5.4346
Max Act: 5.1533. Min Act: -0.1700
Data Index: 1644108 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4346. Min Range: -5.4346
Max Act: 5.1533. Min Act: -0.1700
Data Index: 1466875 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4346. Min Range: -5.4346
Max Act: 5.1221. Min Act: -0.1700
Data Index: 290987 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4346. Min Range: -5.4346
Max Act: 5.1221. Min Act: -0.1700
Data Index: 169976 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4346. Min Range: -5.4346
Max Act: 5.0908. Min Act: -0.1700
Data Index: 3316766 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4346. Min Range: -5.4346
Max Act: 5.0908. Min Act: -0.1700
Data Index: 1653189 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4346. Min Range: -5.4346
Max Act: 5.0908. Min Act: -0.1700
Data Index: 8317286 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4346. Min Range: -5.4346
Max Act: 5.0283. Min Act: -0.1700
Data Index: 2253798 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #19