Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3283 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5988. Min Range: -5.5988
Max Act: 5.5988. Min Act: -0.1700
Data Index: 5121794 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5988. Min Range: -5.5988
Max Act: 5.5363. Min Act: -0.1700
Data Index: 8290484 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5988. Min Range: -5.5988
Max Act: 5.5676. Min Act: -0.1700
Data Index: 7027430 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5988. Min Range: -5.5988
Max Act: 5.5363. Min Act: -0.1700
Data Index: 148129 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5988. Min Range: -5.5988
Max Act: 5.4426. Min Act: -0.1700
Data Index: 1278729 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5988. Min Range: -5.5988
Max Act: 5.4738. Min Act: -0.1700
Data Index: 4997675 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5988. Min Range: -5.5988
Max Act: 5.4738. Min Act: -0.1700
Data Index: 8700892 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5988. Min Range: -5.5988
Max Act: 5.4738. Min Act: -0.1700
Data Index: 5681770 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5988. Min Range: -5.5988
Max Act: 5.4426. Min Act: -0.1700
Data Index: 2594427 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5988. Min Range: -5.5988
Max Act: 5.4426. Min Act: -0.1700
Data Index: 3738832 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5988. Min Range: -5.5988
Max Act: 5.4426. Min Act: -0.1700
Data Index: 1745544 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5988. Min Range: -5.5988
Max Act: 5.4426. Min Act: -0.1700
Data Index: 2620128 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5988. Min Range: -5.5988
Max Act: 5.4113. Min Act: -0.1700
Data Index: 8455947 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5988. Min Range: -5.5988
Max Act: 5.4426. Min Act: -0.1700
Data Index: 5963052 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5988. Min Range: -5.5988
Max Act: 5.4113. Min Act: -0.1700
Data Index: 5121791 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5988. Min Range: -5.5988
Max Act: 5.4113. Min Act: -0.1700
Data Index: 8290487 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5988. Min Range: -5.5988
Max Act: 5.4113. Min Act: -0.1700
Data Index: 3134093 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5988. Min Range: -5.5988
Max Act: 5.3801. Min Act: -0.1700
Data Index: 8000072 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5988. Min Range: -5.5988
Max Act: 5.3801. Min Act: -0.1700
Data Index: 642568 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5988. Min Range: -5.5988
Max Act: 5.3801. Min Act: -0.1700
Data Index: 3772131 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #19