Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3872 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4328. Min Range: -3.4328
Max Act: 3.4328. Min Act: -0.1700
Data Index: 6679006 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4328. Min Range: -3.4328
Max Act: 3.2602. Min Act: -0.1700
Data Index: 8776891 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4328. Min Range: -3.4328
Max Act: 3.1029. Min Act: -0.1700
Data Index: 6032305 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4328. Min Range: -3.4328
Max Act: 3.1029. Min Act: -0.1700
Data Index: 1648121 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4328. Min Range: -3.4328
Max Act: 3.0872. Min Act: -0.1700
Data Index: 2420774 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4328. Min Range: -3.4328
Max Act: 3.1029. Min Act: -0.1700
Data Index: 5603620 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4328. Min Range: -3.4328
Max Act: 3.1029. Min Act: -0.1700
Data Index: 1933764 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4328. Min Range: -3.4328
Max Act: 3.0872. Min Act: -0.1700
Data Index: 3844272 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4328. Min Range: -3.4328
Max Act: 3.0714. Min Act: -0.1700
Data Index: 5199274 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4328. Min Range: -3.4328
Max Act: 3.0556. Min Act: -0.1700
Data Index: 5339569 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4328. Min Range: -3.4328
Max Act: 3.0556. Min Act: -0.1700
Data Index: 4747101 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4328. Min Range: -3.4328
Max Act: 3.0398. Min Act: -0.1700
Data Index: 697212 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4328. Min Range: -3.4328
Max Act: 3.0398. Min Act: -0.1700
Data Index: 6734418 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4328. Min Range: -3.4328
Max Act: 3.0398. Min Act: -0.1700
Data Index: 8684289 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4328. Min Range: -3.4328
Max Act: 3.0398. Min Act: -0.1700
Data Index: 353072 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4328. Min Range: -3.4328
Max Act: 3.0240. Min Act: -0.1700
Data Index: 4680857 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4328. Min Range: -3.4328
Max Act: 3.0083. Min Act: -0.1700
Data Index: 8304183 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4328. Min Range: -3.4328
Max Act: 3.0083. Min Act: -0.1700
Data Index: 4538373 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4328. Min Range: -3.4328
Max Act: 3.0083. Min Act: -0.1700
Data Index: 5453964 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4328. Min Range: -3.4328
Max Act: 3.0083. Min Act: -0.1700
Data Index: 1698331 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #19