Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5108 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.1119. Min Range: -7.1119
Max Act: 7.1119. Min Act: -0.1700
Data Index: 7655226 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1119. Min Range: -7.1119
Max Act: 6.6744. Min Act: -0.1700
Data Index: 7759000 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1119. Min Range: -7.1119
Max Act: 6.6744. Min Act: -0.1700
Data Index: 6641978 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1119. Min Range: -7.1119
Max Act: 6.6119. Min Act: -0.1700
Data Index: 293516 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1119. Min Range: -7.1119
Max Act: 6.6119. Min Act: -0.1700
Data Index: 8262159 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1119. Min Range: -7.1119
Max Act: 6.4869. Min Act: -0.1700
Data Index: 4291356 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1119. Min Range: -7.1119
Max Act: 6.4556. Min Act: -0.1700
Data Index: 3200983 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1119. Min Range: -7.1119
Max Act: 6.4244. Min Act: -0.1700
Data Index: 8169527 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1119. Min Range: -7.1119
Max Act: 6.3931. Min Act: -0.1700
Data Index: 5542878 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1119. Min Range: -7.1119
Max Act: 6.3619. Min Act: -0.1700
Data Index: 5542029 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1119. Min Range: -7.1119
Max Act: 6.3306. Min Act: -0.1700
Data Index: 785505 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1119. Min Range: -7.1119
Max Act: 6.2994. Min Act: -0.1700
Data Index: 3463516 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1119. Min Range: -7.1119
Max Act: 6.2681. Min Act: -0.1700
Data Index: 3200985 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1119. Min Range: -7.1119
Max Act: 6.2681. Min Act: -0.1700
Data Index: 7353980 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1119. Min Range: -7.1119
Max Act: 6.2681. Min Act: -0.1700
Data Index: 4895809 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1119. Min Range: -7.1119
Max Act: 6.2056. Min Act: -0.1700
Data Index: 577167 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1119. Min Range: -7.1119
Max Act: 6.2056. Min Act: -0.1700
Data Index: 1096814 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1119. Min Range: -7.1119
Max Act: 6.2056. Min Act: -0.1700
Data Index: 4993437 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1119. Min Range: -7.1119
Max Act: 6.1744. Min Act: -0.1700
Data Index: 1393523 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1119. Min Range: -7.1119
Max Act: 6.1744. Min Act: -0.1700
Data Index: 3281313 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #19