Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2799 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2830. Min Range: -4.2830
Max Act: 4.2830. Min Act: -0.1700
Data Index: 2466452 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2830. Min Range: -4.2830
Max Act: 4.1580. Min Act: -0.1700
Data Index: 2671907 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2830. Min Range: -4.2830
Max Act: 4.0955. Min Act: -0.1700
Data Index: 8387811 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2830. Min Range: -4.2830
Max Act: 4.0642. Min Act: -0.1700
Data Index: 8223646 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2830. Min Range: -4.2830
Max Act: 4.0642. Min Act: -0.1700
Data Index: 2294072 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2830. Min Range: -4.2830
Max Act: 4.0017. Min Act: -0.1700
Data Index: 1824086 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2830. Min Range: -4.2830
Max Act: 4.0017. Min Act: -0.1700
Data Index: 227748 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2830. Min Range: -4.2830
Max Act: 4.0017. Min Act: -0.1700
Data Index: 7204042 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2830. Min Range: -4.2830
Max Act: 3.9392. Min Act: -0.1700
Data Index: 1550219 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2830. Min Range: -4.2830
Max Act: 3.9392. Min Act: -0.1700
Data Index: 1700675 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2830. Min Range: -4.2830
Max Act: 3.9392. Min Act: -0.1700
Data Index: 1474938 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2830. Min Range: -4.2830
Max Act: 3.9392. Min Act: -0.1700
Data Index: 7548744 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2830. Min Range: -4.2830
Max Act: 3.9392. Min Act: -0.1700
Data Index: 7670731 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2830. Min Range: -4.2830
Max Act: 3.9392. Min Act: -0.1700
Data Index: 370377 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2830. Min Range: -4.2830
Max Act: 3.9392. Min Act: -0.1700
Data Index: 810774 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2830. Min Range: -4.2830
Max Act: 3.9392. Min Act: -0.1700
Data Index: 6765311 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2830. Min Range: -4.2830
Max Act: 3.9392. Min Act: -0.1700
Data Index: 2846320 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2830. Min Range: -4.2830
Max Act: 3.9392. Min Act: -0.1700
Data Index: 1011886 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2830. Min Range: -4.2830
Max Act: 3.9079. Min Act: -0.1700
Data Index: 4475073 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2830. Min Range: -4.2830
Max Act: 3.9236. Min Act: -0.1700
Data Index: 5662068 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #19