Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2884 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3285. Min Range: -6.3285
Max Act: 6.3285. Min Act: -0.1700
Data Index: 7064291 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3285. Min Range: -6.3285
Max Act: 6.2347. Min Act: -0.1700
Data Index: 3497590 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3285. Min Range: -6.3285
Max Act: 6.1722. Min Act: -0.1700
Data Index: 5719698 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3285. Min Range: -6.3285
Max Act: 6.1410. Min Act: -0.1700
Data Index: 4073555 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3285. Min Range: -6.3285
Max Act: 6.1410. Min Act: -0.1700
Data Index: 5799615 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3285. Min Range: -6.3285
Max Act: 6.1097. Min Act: -0.1700
Data Index: 1537748 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3285. Min Range: -6.3285
Max Act: 6.1097. Min Act: -0.1700
Data Index: 6505882 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3285. Min Range: -6.3285
Max Act: 6.0785. Min Act: -0.1700
Data Index: 2524713 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3285. Min Range: -6.3285
Max Act: 6.1097. Min Act: -0.1700
Data Index: 3453647 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3285. Min Range: -6.3285
Max Act: 5.9535. Min Act: -0.1700
Data Index: 8579078 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3285. Min Range: -6.3285
Max Act: 5.9535. Min Act: -0.1700
Data Index: 7717408 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3285. Min Range: -6.3285
Max Act: 5.9222. Min Act: -0.1700
Data Index: 5235892 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3285. Min Range: -6.3285
Max Act: 5.9222. Min Act: -0.1700
Data Index: 5095789 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3285. Min Range: -6.3285
Max Act: 5.9222. Min Act: -0.1700
Data Index: 5476158 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3285. Min Range: -6.3285
Max Act: 5.9222. Min Act: -0.1700
Data Index: 1350277 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3285. Min Range: -6.3285
Max Act: 5.9222. Min Act: -0.1700
Data Index: 8589458 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3285. Min Range: -6.3285
Max Act: 5.8910. Min Act: -0.1700
Data Index: 7896175 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3285. Min Range: -6.3285
Max Act: 5.8597. Min Act: -0.1700
Data Index: 2508197 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3285. Min Range: -6.3285
Max Act: 5.8597. Min Act: -0.1700
Data Index: 8024487 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3285. Min Range: -6.3285
Max Act: 5.8597. Min Act: -0.1700
Data Index: 7155611 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #19