Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4798 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1766. Min Range: -6.1766
Max Act: 6.1766. Min Act: -0.1700
Data Index: 7977257 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1766. Min Range: -6.1766
Max Act: 5.9579. Min Act: -0.1700
Data Index: 6558318 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1766. Min Range: -6.1766
Max Act: 5.8954. Min Act: -0.1700
Data Index: 3841577 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1766. Min Range: -6.1766
Max Act: 5.8954. Min Act: -0.1700
Data Index: 7572710 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1766. Min Range: -6.1766
Max Act: 5.8016. Min Act: -0.1700
Data Index: 654887 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1766. Min Range: -6.1766
Max Act: 5.7704. Min Act: -0.1700
Data Index: 7741891 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1766. Min Range: -6.1766
Max Act: 5.6454. Min Act: -0.1700
Data Index: 732451 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1766. Min Range: -6.1766
Max Act: 5.6454. Min Act: -0.1700
Data Index: 5494574 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1766. Min Range: -6.1766
Max Act: 5.5829. Min Act: -0.1700
Data Index: 7261500 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1766. Min Range: -6.1766
Max Act: 5.6141. Min Act: -0.1700
Data Index: 7468662 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1766. Min Range: -6.1766
Max Act: 5.5829. Min Act: -0.1700
Data Index: 8073004 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1766. Min Range: -6.1766
Max Act: 5.6141. Min Act: -0.1700
Data Index: 5017445 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1766. Min Range: -6.1766
Max Act: 5.5829. Min Act: -0.1700
Data Index: 249860 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1766. Min Range: -6.1766
Max Act: 5.5829. Min Act: -0.1700
Data Index: 3772316 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1766. Min Range: -6.1766
Max Act: 5.5829. Min Act: -0.1700
Data Index: 3865022 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1766. Min Range: -6.1766
Max Act: 5.5516. Min Act: -0.1700
Data Index: 3242048 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1766. Min Range: -6.1766
Max Act: 5.5516. Min Act: -0.1700
Data Index: 7162507 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1766. Min Range: -6.1766
Max Act: 5.5516. Min Act: -0.1700
Data Index: 626724 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1766. Min Range: -6.1766
Max Act: 5.5204. Min Act: -0.1700
Data Index: 6717066 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1766. Min Range: -6.1766
Max Act: 5.5204. Min Act: -0.1700
Data Index: 1992510 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #19