Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3286 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0625. Min Range: -5.0625
Max Act: 5.0625. Min Act: -0.1700
Data Index: 5879909 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0625. Min Range: -5.0625
Max Act: 4.9687. Min Act: -0.1700
Data Index: 399667 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0625. Min Range: -5.0625
Max Act: 5.0000. Min Act: -0.1700
Data Index: 1286019 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0625. Min Range: -5.0625
Max Act: 4.9375. Min Act: -0.1700
Data Index: 1949995 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0625. Min Range: -5.0625
Max Act: 4.8750. Min Act: -0.1700
Data Index: 2470230 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0625. Min Range: -5.0625
Max Act: 4.8437. Min Act: -0.1700
Data Index: 8362804 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0625. Min Range: -5.0625
Max Act: 4.8750. Min Act: -0.1700
Data Index: 1133356 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0625. Min Range: -5.0625
Max Act: 4.8437. Min Act: -0.1700
Data Index: 5536499 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0625. Min Range: -5.0625
Max Act: 4.8437. Min Act: -0.1700
Data Index: 6513202 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0625. Min Range: -5.0625
Max Act: 4.8125. Min Act: -0.1700
Data Index: 4087843 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0625. Min Range: -5.0625
Max Act: 4.7812. Min Act: -0.1700
Data Index: 8190339 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0625. Min Range: -5.0625
Max Act: 4.7812. Min Act: -0.1700
Data Index: 7786039 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0625. Min Range: -5.0625
Max Act: 4.7500. Min Act: -0.1700
Data Index: 2643110 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0625. Min Range: -5.0625
Max Act: 4.6875. Min Act: -0.1700
Data Index: 1688058 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0625. Min Range: -5.0625
Max Act: 4.7187. Min Act: -0.1700
Data Index: 6562393 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0625. Min Range: -5.0625
Max Act: 4.7187. Min Act: -0.1700
Data Index: 1263904 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0625. Min Range: -5.0625
Max Act: 4.6875. Min Act: -0.1700
Data Index: 5751112 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0625. Min Range: -5.0625
Max Act: 4.6875. Min Act: -0.1700
Data Index: 73370 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0625. Min Range: -5.0625
Max Act: 4.6875. Min Act: -0.1700
Data Index: 2397664 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0625. Min Range: -5.0625
Max Act: 4.6875. Min Act: -0.1700
Data Index: 7218074 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #19