Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4840 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3471. Min Range: -3.3471
Max Act: 3.3471. Min Act: -0.1700
Data Index: 177058 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3471. Min Range: -3.3471
Max Act: 3.3000. Min Act: -0.1700
Data Index: 4188172 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3471. Min Range: -3.3471
Max Act: 3.2843. Min Act: -0.1700
Data Index: 4188171 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3471. Min Range: -3.3471
Max Act: 3.2843. Min Act: -0.1700
Data Index: 1567436 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3471. Min Range: -3.3471
Max Act: 3.2686. Min Act: -0.1700
Data Index: 5866850 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3471. Min Range: -3.3471
Max Act: 3.2529. Min Act: -0.1700
Data Index: 3109997 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3471. Min Range: -3.3471
Max Act: 3.2686. Min Act: -0.1700
Data Index: 7735536 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3471. Min Range: -3.3471
Max Act: 3.2371. Min Act: -0.1700
Data Index: 1167396 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3471. Min Range: -3.3471
Max Act: 3.2371. Min Act: -0.1700
Data Index: 8333559 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3471. Min Range: -3.3471
Max Act: 3.2214. Min Act: -0.1700
Data Index: 6485751 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3471. Min Range: -3.3471
Max Act: 3.2214. Min Act: -0.1700
Data Index: 4188173 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3471. Min Range: -3.3471
Max Act: 3.2214. Min Act: -0.1700
Data Index: 941927 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3471. Min Range: -3.3471
Max Act: 3.2057. Min Act: -0.1700
Data Index: 4235919 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3471. Min Range: -3.3471
Max Act: 3.2057. Min Act: -0.1700
Data Index: 1050636 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3471. Min Range: -3.3471
Max Act: 3.1900. Min Act: -0.1700
Data Index: 3901172 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3471. Min Range: -3.3471
Max Act: 3.1900. Min Act: -0.1700
Data Index: 1889273 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3471. Min Range: -3.3471
Max Act: 3.1742. Min Act: -0.1700
Data Index: 270368 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3471. Min Range: -3.3471
Max Act: 3.1900. Min Act: -0.1700
Data Index: 6587552 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3471. Min Range: -3.3471
Max Act: 3.1742. Min Act: -0.1700
Data Index: 5158971 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3471. Min Range: -3.3471
Max Act: 3.1742. Min Act: -0.1700
Data Index: 3859759 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #19