Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5480 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5998. Min Range: -7.5998
Max Act: 7.5998. Min Act: -0.1700
Data Index: 1779699 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5998. Min Range: -7.5998
Max Act: 7.4435. Min Act: -0.1700
Data Index: 1484892 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5998. Min Range: -7.5998
Max Act: 7.4435. Min Act: -0.1700
Data Index: 4761179 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5998. Min Range: -7.5998
Max Act: 7.3498. Min Act: -0.1700
Data Index: 4994931 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5998. Min Range: -7.5998
Max Act: 7.1935. Min Act: -0.1700
Data Index: 2641663 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5998. Min Range: -7.5998
Max Act: 7.1623. Min Act: -0.1700
Data Index: 8118883 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5998. Min Range: -7.5998
Max Act: 7.1623. Min Act: -0.1700
Data Index: 1180426 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5998. Min Range: -7.5998
Max Act: 7.0998. Min Act: -0.1700
Data Index: 933467 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5998. Min Range: -7.5998
Max Act: 6.7560. Min Act: -0.1700
Data Index: 1264849 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5998. Min Range: -7.5998
Max Act: 6.6623. Min Act: -0.1700
Data Index: 4292513 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5998. Min Range: -7.5998
Max Act: 6.5998. Min Act: -0.1700
Data Index: 2527806 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5998. Min Range: -7.5998
Max Act: 6.4748. Min Act: -0.1700
Data Index: 4894470 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5998. Min Range: -7.5998
Max Act: 6.4748. Min Act: -0.1700
Data Index: 3589166 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5998. Min Range: -7.5998
Max Act: 6.4748. Min Act: -0.1700
Data Index: 5513988 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5998. Min Range: -7.5998
Max Act: 6.4435. Min Act: -0.1700
Data Index: 7918993 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5998. Min Range: -7.5998
Max Act: 6.4123. Min Act: -0.1700
Data Index: 543209 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5998. Min Range: -7.5998
Max Act: 6.4123. Min Act: -0.1700
Data Index: 1131989 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5998. Min Range: -7.5998
Max Act: 6.3810. Min Act: -0.1700
Data Index: 4122642 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5998. Min Range: -7.5998
Max Act: 6.3810. Min Act: -0.1700
Data Index: 7734479 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5998. Min Range: -7.5998
Max Act: 6.3810. Min Act: -0.1700
Data Index: 3708458 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #19