Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1715 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6266. Min Range: -6.6266
Max Act: 6.6266. Min Act: -0.1700
Data Index: 5123795 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6266. Min Range: -6.6266
Max Act: 6.5016. Min Act: -0.1700
Data Index: 5123801 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6266. Min Range: -6.6266
Max Act: 6.3141. Min Act: -0.1700
Data Index: 6243308 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6266. Min Range: -6.6266
Max Act: 6.3141. Min Act: -0.1700
Data Index: 5664419 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6266. Min Range: -6.6266
Max Act: 6.1891. Min Act: -0.1700
Data Index: 8712408 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6266. Min Range: -6.6266
Max Act: 6.0016. Min Act: -0.1700
Data Index: 2932782 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6266. Min Range: -6.6266
Max Act: 6.0016. Min Act: -0.1700
Data Index: 8542123 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6266. Min Range: -6.6266
Max Act: 6.0016. Min Act: -0.1700
Data Index: 6623493 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6266. Min Range: -6.6266
Max Act: 5.9704. Min Act: -0.1700
Data Index: 6425495 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6266. Min Range: -6.6266
Max Act: 5.9079. Min Act: -0.1700
Data Index: 342265 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6266. Min Range: -6.6266
Max Act: 5.8766. Min Act: -0.1700
Data Index: 8078891 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6266. Min Range: -6.6266
Max Act: 5.9079. Min Act: -0.1700
Data Index: 6024099 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6266. Min Range: -6.6266
Max Act: 5.8766. Min Act: -0.1700
Data Index: 6744294 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6266. Min Range: -6.6266
Max Act: 5.8454. Min Act: -0.1700
Data Index: 7051955 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6266. Min Range: -6.6266
Max Act: 5.8141. Min Act: -0.1700
Data Index: 8027885 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6266. Min Range: -6.6266
Max Act: 5.8141. Min Act: -0.1700
Data Index: 7664688 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6266. Min Range: -6.6266
Max Act: 5.8141. Min Act: -0.1700
Data Index: 1518733 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6266. Min Range: -6.6266
Max Act: 5.8141. Min Act: -0.1700
Data Index: 5585168 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6266. Min Range: -6.6266
Max Act: 5.7829. Min Act: -0.1700
Data Index: 8642603 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6266. Min Range: -6.6266
Max Act: 5.7829. Min Act: -0.1700
Data Index: 2694885 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #19