Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4038 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.2592. Min Range: -10.2592
Max Act: 10.2592. Min Act: -0.1700
Data Index: 4914127 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.2592. Min Range: -10.2592
Max Act: 9.5092. Min Act: -0.1700
Data Index: 8261503 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.2592. Min Range: -10.2592
Max Act: 9.5092. Min Act: -0.1700
Data Index: 4173019 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.2592. Min Range: -10.2592
Max Act: 9.3217. Min Act: -0.1700
Data Index: 1447777 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.2592. Min Range: -10.2592
Max Act: 9.3217. Min Act: -0.1700
Data Index: 5843325 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.2592. Min Range: -10.2592
Max Act: 9.3217. Min Act: -0.1700
Data Index: 456400 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.2592. Min Range: -10.2592
Max Act: 9.1967. Min Act: -0.1700
Data Index: 440781 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.2592. Min Range: -10.2592
Max Act: 9.1967. Min Act: -0.1700
Data Index: 1945993 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.2592. Min Range: -10.2592
Max Act: 9.1342. Min Act: -0.1698
Data Index: 2430450 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.2592. Min Range: -10.2592
Max Act: 9.1342. Min Act: -0.1700
Data Index: 6526011 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.2592. Min Range: -10.2592
Max Act: 9.1342. Min Act: -0.1700
Data Index: 243108 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.2592. Min Range: -10.2592
Max Act: 9.0717. Min Act: -0.1700
Data Index: 1957344 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.2592. Min Range: -10.2592
Max Act: 9.0717. Min Act: -0.1700
Data Index: 5938076 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.2592. Min Range: -10.2592
Max Act: 9.0717. Min Act: -0.1700
Data Index: 768878 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.2592. Min Range: -10.2592
Max Act: 9.0092. Min Act: -0.1700
Data Index: 8674420 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.2592. Min Range: -10.2592
Max Act: 9.0092. Min Act: -0.1700
Data Index: 8182642 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.2592. Min Range: -10.2592
Max Act: 8.9467. Min Act: -0.1700
Data Index: 2006655 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.2592. Min Range: -10.2592
Max Act: 8.9467. Min Act: -0.1700
Data Index: 1255264 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.2592. Min Range: -10.2592
Max Act: 8.9467. Min Act: -0.1700
Data Index: 1379346 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.2592. Min Range: -10.2592
Max Act: 8.9467. Min Act: -0.1700
Data Index: 8244227 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #19