Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2893 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7252. Min Range: -6.7252
Max Act: 6.7252. Min Act: -0.1700
Data Index: 6005675 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7252. Min Range: -6.7252
Max Act: 6.2564. Min Act: -0.1700
Data Index: 1517732 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7252. Min Range: -6.7252
Max Act: 6.1002. Min Act: -0.1700
Data Index: 4785768 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7252. Min Range: -6.7252
Max Act: 6.0377. Min Act: -0.1700
Data Index: 8462737 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7252. Min Range: -6.7252
Max Act: 5.9752. Min Act: -0.1700
Data Index: 2494765 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7252. Min Range: -6.7252
Max Act: 5.9127. Min Act: -0.1700
Data Index: 8674362 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7252. Min Range: -6.7252
Max Act: 5.8814. Min Act: -0.1700
Data Index: 634617 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7252. Min Range: -6.7252
Max Act: 5.8814. Min Act: -0.1700
Data Index: 2833701 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7252. Min Range: -6.7252
Max Act: 5.8814. Min Act: -0.1700
Data Index: 4785767 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7252. Min Range: -6.7252
Max Act: 5.8502. Min Act: -0.1700
Data Index: 8726551 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7252. Min Range: -6.7252
Max Act: 5.8502. Min Act: -0.1700
Data Index: 7545731 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7252. Min Range: -6.7252
Max Act: 5.8189. Min Act: -0.1700
Data Index: 7745334 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7252. Min Range: -6.7252
Max Act: 5.8189. Min Act: -0.1700
Data Index: 5561520 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7252. Min Range: -6.7252
Max Act: 5.8189. Min Act: -0.1700
Data Index: 4920897 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7252. Min Range: -6.7252
Max Act: 5.7564. Min Act: -0.1700
Data Index: 1570607 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7252. Min Range: -6.7252
Max Act: 5.8189. Min Act: -0.1700
Data Index: 6310144 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7252. Min Range: -6.7252
Max Act: 5.7877. Min Act: -0.1700
Data Index: 1202176 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7252. Min Range: -6.7252
Max Act: 5.7564. Min Act: -0.1700
Data Index: 6277158 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7252. Min Range: -6.7252
Max Act: 5.7877. Min Act: -0.1700
Data Index: 6285720 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7252. Min Range: -6.7252
Max Act: 5.7877. Min Act: -0.1699
Data Index: 1502213 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #19