Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3829 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1986. Min Range: -5.1986
Max Act: 5.1986. Min Act: -0.1700
Data Index: 2525673 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1986. Min Range: -5.1986
Max Act: 5.1673. Min Act: -0.1700
Data Index: 7630161 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1986. Min Range: -5.1986
Max Act: 5.0736. Min Act: -0.1700
Data Index: 1919740 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1986. Min Range: -5.1986
Max Act: 5.1048. Min Act: -0.1700
Data Index: 597421 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1986. Min Range: -5.1986
Max Act: 5.0423. Min Act: -0.1700
Data Index: 6034817 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1986. Min Range: -5.1986
Max Act: 5.0423. Min Act: -0.1700
Data Index: 1589759 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1986. Min Range: -5.1986
Max Act: 5.0111. Min Act: -0.1700
Data Index: 4727624 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1986. Min Range: -5.1986
Max Act: 4.9798. Min Act: -0.1700
Data Index: 1637129 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1986. Min Range: -5.1986
Max Act: 5.0111. Min Act: -0.1700
Data Index: 7212522 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1986. Min Range: -5.1986
Max Act: 5.0111. Min Act: -0.1700
Data Index: 6138241 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1986. Min Range: -5.1986
Max Act: 4.9798. Min Act: -0.1700
Data Index: 4727625 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1986. Min Range: -5.1986
Max Act: 4.9798. Min Act: -0.1700
Data Index: 7272426 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1986. Min Range: -5.1986
Max Act: 4.9798. Min Act: -0.1700
Data Index: 1870270 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1986. Min Range: -5.1986
Max Act: 4.9798. Min Act: -0.1700
Data Index: 4961075 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1986. Min Range: -5.1986
Max Act: 4.9798. Min Act: -0.1700
Data Index: 7416250 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1986. Min Range: -5.1986
Max Act: 4.9798. Min Act: -0.1700
Data Index: 2401445 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1986. Min Range: -5.1986
Max Act: 4.9485. Min Act: -0.1700
Data Index: 4722896 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1986. Min Range: -5.1986
Max Act: 4.9485. Min Act: -0.1700
Data Index: 4871695 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1986. Min Range: -5.1986
Max Act: 4.9173. Min Act: -0.1700
Data Index: 6343795 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1986. Min Range: -5.1986
Max Act: 4.9173. Min Act: -0.1700
Data Index: 5604155 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #19