Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5693 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6430. Min Range: -7.6430
Max Act: 7.6430. Min Act: -0.1700
Data Index: 5365896 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6430. Min Range: -7.6430
Max Act: 7.5805. Min Act: -0.1700
Data Index: 3509608 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6430. Min Range: -7.6430
Max Act: 7.3930. Min Act: -0.1700
Data Index: 455099 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6430. Min Range: -7.6430
Max Act: 7.3930. Min Act: -0.1700
Data Index: 2258973 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6430. Min Range: -7.6430
Max Act: 7.3617. Min Act: -0.1700
Data Index: 4962028 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6430. Min Range: -7.6430
Max Act: 7.3305. Min Act: -0.1700
Data Index: 8023922 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6430. Min Range: -7.6430
Max Act: 7.2992. Min Act: -0.1700
Data Index: 8516190 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6430. Min Range: -7.6430
Max Act: 7.2680. Min Act: -0.1700
Data Index: 2961756 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6430. Min Range: -7.6430
Max Act: 7.2367. Min Act: -0.1700
Data Index: 7121828 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6430. Min Range: -7.6430
Max Act: 7.1742. Min Act: -0.1700
Data Index: 3063142 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6430. Min Range: -7.6430
Max Act: 7.1430. Min Act: -0.1700
Data Index: 1498219 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6430. Min Range: -7.6430
Max Act: 7.0805. Min Act: -0.1700
Data Index: 8252531 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6430. Min Range: -7.6430
Max Act: 7.0805. Min Act: -0.1700
Data Index: 3820472 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6430. Min Range: -7.6430
Max Act: 7.0805. Min Act: -0.1700
Data Index: 5484850 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6430. Min Range: -7.6430
Max Act: 7.1117. Min Act: -0.1700
Data Index: 1433469 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6430. Min Range: -7.6430
Max Act: 7.0492. Min Act: -0.1700
Data Index: 2050766 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6430. Min Range: -7.6430
Max Act: 7.0492. Min Act: -0.1700
Data Index: 784535 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6430. Min Range: -7.6430
Max Act: 7.0180. Min Act: -0.1700
Data Index: 1828465 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6430. Min Range: -7.6430
Max Act: 6.9555. Min Act: -0.1700
Data Index: 63857 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6430. Min Range: -7.6430
Max Act: 6.9867. Min Act: -0.1700
Data Index: 1786114 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #19