Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3795 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0244. Min Range: -4.0244
Max Act: 4.0244. Min Act: -0.1700
Data Index: 2955156 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0244. Min Range: -4.0244
Max Act: 4.0088. Min Act: -0.1700
Data Index: 4478149 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0244. Min Range: -4.0244
Max Act: 3.9150. Min Act: -0.1700
Data Index: 7762314 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0244. Min Range: -4.0244
Max Act: 3.9150. Min Act: -0.1700
Data Index: 1086887 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0244. Min Range: -4.0244
Max Act: 3.9150. Min Act: -0.1700
Data Index: 7375911 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0244. Min Range: -4.0244
Max Act: 3.9150. Min Act: -0.1700
Data Index: 1440602 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0244. Min Range: -4.0244
Max Act: 3.8212. Min Act: -0.1700
Data Index: 7034870 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0244. Min Range: -4.0244
Max Act: 3.8212. Min Act: -0.1700
Data Index: 460187 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0244. Min Range: -4.0244
Max Act: 3.8055. Min Act: -0.1700
Data Index: 1552886 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0244. Min Range: -4.0244
Max Act: 3.8212. Min Act: -0.1700
Data Index: 3629971 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0244. Min Range: -4.0244
Max Act: 3.8055. Min Act: -0.1700
Data Index: 6524366 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0244. Min Range: -4.0244
Max Act: 3.8055. Min Act: -0.1700
Data Index: 5757246 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0244. Min Range: -4.0244
Max Act: 3.7899. Min Act: -0.1700
Data Index: 7244633 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0244. Min Range: -4.0244
Max Act: 3.7743. Min Act: -0.1700
Data Index: 615078 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0244. Min Range: -4.0244
Max Act: 3.7743. Min Act: -0.1700
Data Index: 7776796 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0244. Min Range: -4.0244
Max Act: 3.7586. Min Act: -0.1700
Data Index: 1377246 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0244. Min Range: -4.0244
Max Act: 3.7586. Min Act: -0.1700
Data Index: 8742401 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0244. Min Range: -4.0244
Max Act: 3.7430. Min Act: -0.1700
Data Index: 7004235 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0244. Min Range: -4.0244
Max Act: 3.7117. Min Act: -0.1700
Data Index: 2257927 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0244. Min Range: -4.0244
Max Act: 3.7117. Min Act: -0.1700
Data Index: 6583250 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #19