Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 120 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9873. Min Range: -6.9873
Max Act: 6.9873. Min Act: -0.1700
Data Index: 5786980 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9873. Min Range: -6.9873
Max Act: 6.8623. Min Act: -0.1700
Data Index: 3314425 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9873. Min Range: -6.9873
Max Act: 6.8623. Min Act: -0.1700
Data Index: 2768672 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9873. Min Range: -6.9873
Max Act: 6.8623. Min Act: -0.1700
Data Index: 6288931 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9873. Min Range: -6.9873
Max Act: 6.7061. Min Act: -0.1700
Data Index: 4783992 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9873. Min Range: -6.9873
Max Act: 6.7061. Min Act: -0.1700
Data Index: 895080 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9873. Min Range: -6.9873
Max Act: 6.7061. Min Act: -0.1700
Data Index: 23144 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9873. Min Range: -6.9873
Max Act: 6.6748. Min Act: -0.1700
Data Index: 2583743 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9873. Min Range: -6.9873
Max Act: 6.6436. Min Act: -0.1700
Data Index: 8281412 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9873. Min Range: -6.9873
Max Act: 6.6436. Min Act: -0.1700
Data Index: 6203986 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9873. Min Range: -6.9873
Max Act: 6.6436. Min Act: -0.1700
Data Index: 1844790 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9873. Min Range: -6.9873
Max Act: 6.6123. Min Act: -0.1700
Data Index: 625043 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9873. Min Range: -6.9873
Max Act: 6.6123. Min Act: -0.1700
Data Index: 7062729 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9873. Min Range: -6.9873
Max Act: 6.6123. Min Act: -0.1700
Data Index: 1723562 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9873. Min Range: -6.9873
Max Act: 6.5498. Min Act: -0.1700
Data Index: 5533720 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9873. Min Range: -6.9873
Max Act: 6.5186. Min Act: -0.1700
Data Index: 5511408 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9873. Min Range: -6.9873
Max Act: 6.4873. Min Act: -0.1700
Data Index: 2265969 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9873. Min Range: -6.9873
Max Act: 6.5186. Min Act: -0.1700
Data Index: 6944846 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9873. Min Range: -6.9873
Max Act: 6.5186. Min Act: -0.1700
Data Index: 5695658 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9873. Min Range: -6.9873
Max Act: 6.4873. Min Act: -0.1700
Data Index: 1389137 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #19