Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2857 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6805. Min Range: -6.6805
Max Act: 6.6805. Min Act: -0.1700
Data Index: 3431791 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6805. Min Range: -6.6805
Max Act: 6.6493. Min Act: -0.1700
Data Index: 6199378 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6805. Min Range: -6.6805
Max Act: 6.5555. Min Act: -0.1700
Data Index: 5215176 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6805. Min Range: -6.6805
Max Act: 6.5243. Min Act: -0.1700
Data Index: 737833 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6805. Min Range: -6.6805
Max Act: 6.5555. Min Act: -0.1700
Data Index: 5515623 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6805. Min Range: -6.6805
Max Act: 6.5243. Min Act: -0.1700
Data Index: 496714 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6805. Min Range: -6.6805
Max Act: 6.4930. Min Act: -0.1700
Data Index: 8186477 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6805. Min Range: -6.6805
Max Act: 6.5243. Min Act: -0.1700
Data Index: 1777270 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6805. Min Range: -6.6805
Max Act: 6.3993. Min Act: -0.1700
Data Index: 1316526 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6805. Min Range: -6.6805
Max Act: 6.3368. Min Act: -0.1700
Data Index: 3466729 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6805. Min Range: -6.6805
Max Act: 6.3055. Min Act: -0.1700
Data Index: 8258667 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6805. Min Range: -6.6805
Max Act: 6.3055. Min Act: -0.1700
Data Index: 6472208 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6805. Min Range: -6.6805
Max Act: 6.2743. Min Act: -0.1700
Data Index: 4390261 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6805. Min Range: -6.6805
Max Act: 6.2743. Min Act: -0.1700
Data Index: 2621714 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6805. Min Range: -6.6805
Max Act: 6.2743. Min Act: -0.1700
Data Index: 7745550 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6805. Min Range: -6.6805
Max Act: 6.2743. Min Act: -0.1700
Data Index: 1662771 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6805. Min Range: -6.6805
Max Act: 6.2743. Min Act: -0.1700
Data Index: 5464706 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6805. Min Range: -6.6805
Max Act: 6.2430. Min Act: -0.1700
Data Index: 6451066 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6805. Min Range: -6.6805
Max Act: 6.2430. Min Act: -0.1700
Data Index: 4545651 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6805. Min Range: -6.6805
Max Act: 6.2118. Min Act: -0.1700
Data Index: 8016646 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #19