Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4287 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.5998. Min Range: -7.5998
Max Act: 7.5998. Min Act: -0.1700
Data Index: 7891936 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5998. Min Range: -7.5998
Max Act: 7.2560. Min Act: -0.1700
Data Index: 6623440 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5998. Min Range: -7.5998
Max Act: 7.1310. Min Act: -0.1700
Data Index: 5076060 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5998. Min Range: -7.5998
Max Act: 7.0685. Min Act: -0.1700
Data Index: 4633808 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5998. Min Range: -7.5998
Max Act: 7.0060. Min Act: -0.1700
Data Index: 3532678 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5998. Min Range: -7.5998
Max Act: 7.0060. Min Act: -0.1700
Data Index: 4723662 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5998. Min Range: -7.5998
Max Act: 6.9435. Min Act: -0.1700
Data Index: 5598653 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5998. Min Range: -7.5998
Max Act: 6.9123. Min Act: -0.1700
Data Index: 4525742 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5998. Min Range: -7.5998
Max Act: 6.9123. Min Act: -0.1700
Data Index: 4710568 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5998. Min Range: -7.5998
Max Act: 6.8810. Min Act: -0.1700
Data Index: 4365544 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5998. Min Range: -7.5998
Max Act: 6.8810. Min Act: -0.1700
Data Index: 6416223 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5998. Min Range: -7.5998
Max Act: 6.8810. Min Act: -0.1700
Data Index: 8163073 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5998. Min Range: -7.5998
Max Act: 6.8810. Min Act: -0.1700
Data Index: 3395691 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5998. Min Range: -7.5998
Max Act: 6.8498. Min Act: -0.1700
Data Index: 2785322 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5998. Min Range: -7.5998
Max Act: 6.8810. Min Act: -0.1700
Data Index: 6323288 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5998. Min Range: -7.5998
Max Act: 6.8498. Min Act: -0.1700
Data Index: 2004890 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5998. Min Range: -7.5998
Max Act: 6.8185. Min Act: -0.1700
Data Index: 7692160 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5998. Min Range: -7.5998
Max Act: 6.7873. Min Act: -0.1700
Data Index: 3935651 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5998. Min Range: -7.5998
Max Act: 6.7873. Min Act: -0.1700
Data Index: 5907396 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5998. Min Range: -7.5998
Max Act: 6.8185. Min Act: -0.1700
Data Index: 5671529 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #19