Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3305 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.8634. Min Range: -2.8634
Max Act: 2.8634. Min Act: -0.1700
Data Index: 5673085 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8634. Min Range: -2.8634
Max Act: 2.8157. Min Act: -0.1700
Data Index: 2661712 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8634. Min Range: -2.8634
Max Act: 2.7998. Min Act: -0.1700
Data Index: 5375788 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8634. Min Range: -2.8634
Max Act: 2.7679. Min Act: -0.1700
Data Index: 2993550 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8634. Min Range: -2.8634
Max Act: 2.7679. Min Act: -0.1700
Data Index: 584663 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8634. Min Range: -2.8634
Max Act: 2.7679. Min Act: -0.1700
Data Index: 307711 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8634. Min Range: -2.8634
Max Act: 2.7679. Min Act: -0.1700
Data Index: 804940 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8634. Min Range: -2.8634
Max Act: 2.7679. Min Act: -0.1700
Data Index: 5430524 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8634. Min Range: -2.8634
Max Act: 2.7520. Min Act: -0.1700
Data Index: 156871 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8634. Min Range: -2.8634
Max Act: 2.7520. Min Act: -0.1700
Data Index: 5672980 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8634. Min Range: -2.8634
Max Act: 2.7520. Min Act: -0.1700
Data Index: 57679 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8634. Min Range: -2.8634
Max Act: 2.7520. Min Act: -0.1700
Data Index: 3844622 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8634. Min Range: -2.8634
Max Act: 2.7360. Min Act: -0.1700
Data Index: 1672545 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8634. Min Range: -2.8634
Max Act: 2.7360. Min Act: -0.1700
Data Index: 7809413 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8634. Min Range: -2.8634
Max Act: 2.7360. Min Act: -0.1700
Data Index: 3190304 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8634. Min Range: -2.8634
Max Act: 2.7360. Min Act: -0.1700
Data Index: 8356982 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8634. Min Range: -2.8634
Max Act: 2.7360. Min Act: -0.1700
Data Index: 1944106 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8634. Min Range: -2.8634
Max Act: 2.7200. Min Act: -0.1700
Data Index: 5300779 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8634. Min Range: -2.8634
Max Act: 2.7200. Min Act: -0.1700
Data Index: 5300785 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8634. Min Range: -2.8634
Max Act: 2.7200. Min Act: -0.1700
Data Index: 491263 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #19