Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 175 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0857. Min Range: -8.0857
Max Act: 8.0857. Min Act: -0.1700
Data Index: 8565458 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0857. Min Range: -8.0857
Max Act: 7.8982. Min Act: -0.1700
Data Index: 8656204 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0857. Min Range: -8.0857
Max Act: 7.7732. Min Act: -0.1700
Data Index: 2550952 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0857. Min Range: -8.0857
Max Act: 7.7732. Min Act: -0.1700
Data Index: 4644209 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0857. Min Range: -8.0857
Max Act: 7.7107. Min Act: -0.1700
Data Index: 8253549 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0857. Min Range: -8.0857
Max Act: 7.7107. Min Act: -0.1700
Data Index: 8344262 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0857. Min Range: -8.0857
Max Act: 7.6170. Min Act: -0.1700
Data Index: 1150310 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0857. Min Range: -8.0857
Max Act: 7.6170. Min Act: -0.1700
Data Index: 8530276 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0857. Min Range: -8.0857
Max Act: 7.5857. Min Act: -0.1700
Data Index: 4619012 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0857. Min Range: -8.0857
Max Act: 7.5232. Min Act: -0.1700
Data Index: 4357385 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0857. Min Range: -8.0857
Max Act: 7.5545. Min Act: -0.1700
Data Index: 7642487 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0857. Min Range: -8.0857
Max Act: 7.5232. Min Act: -0.1700
Data Index: 2582690 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0857. Min Range: -8.0857
Max Act: 7.5545. Min Act: -0.1700
Data Index: 5277146 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0857. Min Range: -8.0857
Max Act: 7.5232. Min Act: -0.1700
Data Index: 1022564 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0857. Min Range: -8.0857
Max Act: 7.5232. Min Act: -0.1700
Data Index: 1886134 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0857. Min Range: -8.0857
Max Act: 7.4920. Min Act: -0.1700
Data Index: 3128455 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0857. Min Range: -8.0857
Max Act: 7.4607. Min Act: -0.1700
Data Index: 2046801 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0857. Min Range: -8.0857
Max Act: 7.4607. Min Act: -0.1700
Data Index: 68226 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0857. Min Range: -8.0857
Max Act: 7.4607. Min Act: -0.1700
Data Index: 5861923 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0857. Min Range: -8.0857
Max Act: 7.4607. Min Act: -0.1700
Data Index: 7008868 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #19