Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2874 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6725. Min Range: -8.6725
Max Act: 8.6725. Min Act: -0.1700
Data Index: 6372230 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6725. Min Range: -8.6725
Max Act: 8.6725. Min Act: -0.1700
Data Index: 6276171 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6725. Min Range: -8.6725
Max Act: 8.6100. Min Act: -0.1700
Data Index: 6873955 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6725. Min Range: -8.6725
Max Act: 8.5475. Min Act: -0.1700
Data Index: 2339646 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6725. Min Range: -8.6725
Max Act: 8.4850. Min Act: -0.1700
Data Index: 5912943 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6725. Min Range: -8.6725
Max Act: 8.4850. Min Act: -0.1700
Data Index: 6091117 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6725. Min Range: -8.6725
Max Act: 8.3600. Min Act: -0.1700
Data Index: 5227948 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6725. Min Range: -8.6725
Max Act: 8.3600. Min Act: -0.1700
Data Index: 4928140 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6725. Min Range: -8.6725
Max Act: 8.2350. Min Act: -0.1700
Data Index: 45062 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6725. Min Range: -8.6725
Max Act: 8.1725. Min Act: -0.1700
Data Index: 3981184 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6725. Min Range: -8.6725
Max Act: 8.1725. Min Act: -0.1700
Data Index: 5232240 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6725. Min Range: -8.6725
Max Act: 8.1100. Min Act: -0.1700
Data Index: 1151478 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6725. Min Range: -8.6725
Max Act: 8.1100. Min Act: -0.1700
Data Index: 2334548 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6725. Min Range: -8.6725
Max Act: 8.1100. Min Act: -0.1700
Data Index: 7490707 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6725. Min Range: -8.6725
Max Act: 8.0475. Min Act: -0.1700
Data Index: 103948 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6725. Min Range: -8.6725
Max Act: 8.0475. Min Act: -0.1700
Data Index: 3415155 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6725. Min Range: -8.6725
Max Act: 7.9850. Min Act: -0.1700
Data Index: 8553549 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6725. Min Range: -8.6725
Max Act: 8.0475. Min Act: -0.1700
Data Index: 1026758 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6725. Min Range: -8.6725
Max Act: 7.9850. Min Act: -0.1700
Data Index: 69253 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6725. Min Range: -8.6725
Max Act: 7.9850. Min Act: -0.1700
Data Index: 6907615 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #19