Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1747 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.8027. Min Range: -2.8027
Max Act: 2.8027. Min Act: -0.1700
Data Index: 3714641 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8027. Min Range: -2.8027
Max Act: 2.7389. Min Act: -0.1700
Data Index: 5726847 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8027. Min Range: -2.8027
Max Act: 2.6909. Min Act: -0.1700
Data Index: 7834014 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8027. Min Range: -2.8027
Max Act: 2.6909. Min Act: -0.1700
Data Index: 7079235 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8027. Min Range: -2.8027
Max Act: 2.6589. Min Act: -0.1700
Data Index: 4177829 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8027. Min Range: -2.8027
Max Act: 2.6589. Min Act: -0.1700
Data Index: 440926 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8027. Min Range: -2.8027
Max Act: 2.6589. Min Act: -0.1700
Data Index: 3937103 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8027. Min Range: -2.8027
Max Act: 2.6429. Min Act: -0.1700
Data Index: 3566123 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8027. Min Range: -2.8027
Max Act: 2.6268. Min Act: -0.1700
Data Index: 6719805 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8027. Min Range: -2.8027
Max Act: 2.6429. Min Act: -0.1700
Data Index: 8810322 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8027. Min Range: -2.8027
Max Act: 2.6429. Min Act: -0.1700
Data Index: 7719154 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8027. Min Range: -2.8027
Max Act: 2.6268. Min Act: -0.1700
Data Index: 4076914 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8027. Min Range: -2.8027
Max Act: 2.6107. Min Act: -0.1700
Data Index: 4739079 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8027. Min Range: -2.8027
Max Act: 2.6268. Min Act: -0.1700
Data Index: 337254 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8027. Min Range: -2.8027
Max Act: 2.6268. Min Act: -0.1700
Data Index: 1898951 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8027. Min Range: -2.8027
Max Act: 2.6429. Min Act: -0.1700
Data Index: 1402446 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8027. Min Range: -2.8027
Max Act: 2.6107. Min Act: -0.1700
Data Index: 7340807 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8027. Min Range: -2.8027
Max Act: 2.6107. Min Act: -0.1700
Data Index: 1527334 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8027. Min Range: -2.8027
Max Act: 2.5946. Min Act: -0.1700
Data Index: 4525175 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8027. Min Range: -2.8027
Max Act: 2.6107. Min Act: -0.1700
Data Index: 469760 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #19