Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1773 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3452. Min Range: -5.3452
Max Act: 5.3452. Min Act: -0.1700
Data Index: 814076 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3452. Min Range: -5.3452
Max Act: 5.1577. Min Act: -0.1700
Data Index: 5305382 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3452. Min Range: -5.3452
Max Act: 5.0015. Min Act: -0.1700
Data Index: 1930472 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3452. Min Range: -5.3452
Max Act: 4.9390. Min Act: -0.1696
Data Index: 2796352 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3452. Min Range: -5.3452
Max Act: 4.9390. Min Act: -0.1700
Data Index: 5373004 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3452. Min Range: -5.3452
Max Act: 4.9390. Min Act: -0.1700
Data Index: 8592066 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3452. Min Range: -5.3452
Max Act: 4.9077. Min Act: -0.1700
Data Index: 616336 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3452. Min Range: -5.3452
Max Act: 4.8765. Min Act: -0.1700
Data Index: 7074685 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3452. Min Range: -5.3452
Max Act: 4.8765. Min Act: -0.1700
Data Index: 6164109 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3452. Min Range: -5.3452
Max Act: 4.8765. Min Act: -0.1700
Data Index: 4136502 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3452. Min Range: -5.3452
Max Act: 4.8452. Min Act: -0.1700
Data Index: 2255300 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3452. Min Range: -5.3452
Max Act: 4.8452. Min Act: -0.1700
Data Index: 3543210 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3452. Min Range: -5.3452
Max Act: 4.8452. Min Act: -0.1697
Data Index: 960999 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3452. Min Range: -5.3452
Max Act: 4.8452. Min Act: -0.1700
Data Index: 6373789 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3452. Min Range: -5.3452
Max Act: 4.8452. Min Act: -0.1700
Data Index: 4352228 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3452. Min Range: -5.3452
Max Act: 4.8140. Min Act: -0.1700
Data Index: 2003228 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3452. Min Range: -5.3452
Max Act: 4.8140. Min Act: -0.1700
Data Index: 8236848 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3452. Min Range: -5.3452
Max Act: 4.8140. Min Act: -0.1700
Data Index: 2463440 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3452. Min Range: -5.3452
Max Act: 4.8140. Min Act: -0.1700
Data Index: 1387396 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3452. Min Range: -5.3452
Max Act: 4.8140. Min Act: -0.1700
Data Index: 8587098 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #19