Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3190 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0727. Min Range: -5.0727
Max Act: 5.0727. Min Act: -0.1700
Data Index: 544676 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0727. Min Range: -5.0727
Max Act: 4.8852. Min Act: -0.1700
Data Index: 8372483 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0727. Min Range: -5.0727
Max Act: 4.8540. Min Act: -0.1700
Data Index: 6268289 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0727. Min Range: -5.0727
Max Act: 4.8540. Min Act: -0.1700
Data Index: 5706873 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0727. Min Range: -5.0727
Max Act: 4.8540. Min Act: -0.1700
Data Index: 1210398 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0727. Min Range: -5.0727
Max Act: 4.8540. Min Act: -0.1700
Data Index: 205853 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0727. Min Range: -5.0727
Max Act: 4.7915. Min Act: -0.1700
Data Index: 2157889 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0727. Min Range: -5.0727
Max Act: 4.7915. Min Act: -0.1700
Data Index: 5706882 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0727. Min Range: -5.0727
Max Act: 4.7915. Min Act: -0.1700
Data Index: 3227957 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0727. Min Range: -5.0727
Max Act: 4.7290. Min Act: -0.1700
Data Index: 1119714 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0727. Min Range: -5.0727
Max Act: 4.7290. Min Act: -0.1700
Data Index: 752266 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0727. Min Range: -5.0727
Max Act: 4.7602. Min Act: -0.1700
Data Index: 5706875 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0727. Min Range: -5.0727
Max Act: 4.7290. Min Act: -0.1700
Data Index: 217575 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0727. Min Range: -5.0727
Max Act: 4.6977. Min Act: -0.1700
Data Index: 3049764 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0727. Min Range: -5.0727
Max Act: 4.6977. Min Act: -0.1700
Data Index: 3350164 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0727. Min Range: -5.0727
Max Act: 4.6665. Min Act: -0.1700
Data Index: 4516748 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0727. Min Range: -5.0727
Max Act: 4.6665. Min Act: -0.1700
Data Index: 5706866 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0727. Min Range: -5.0727
Max Act: 4.6665. Min Act: -0.1700
Data Index: 6522122 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0727. Min Range: -5.0727
Max Act: 4.6977. Min Act: -0.1700
Data Index: 5706871 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0727. Min Range: -5.0727
Max Act: 4.6665. Min Act: -0.1700
Data Index: 4516741 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #19