Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5375 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1144. Min Range: -5.1144
Max Act: 5.1144. Min Act: -0.1700
Data Index: 7970601 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1144. Min Range: -5.1144
Max Act: 5.0519. Min Act: -0.1700
Data Index: 5442220 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1144. Min Range: -5.1144
Max Act: 4.9894. Min Act: -0.1700
Data Index: 704929 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1144. Min Range: -5.1144
Max Act: 4.9581. Min Act: -0.1700
Data Index: 175910 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1144. Min Range: -5.1144
Max Act: 4.9894. Min Act: -0.1700
Data Index: 8045739 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1144. Min Range: -5.1144
Max Act: 4.9581. Min Act: -0.1700
Data Index: 4000555 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1144. Min Range: -5.1144
Max Act: 4.9269. Min Act: -0.1700
Data Index: 6656800 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1144. Min Range: -5.1144
Max Act: 4.9269. Min Act: -0.1700
Data Index: 943560 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1144. Min Range: -5.1144
Max Act: 4.8956. Min Act: -0.1700
Data Index: 6504639 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1144. Min Range: -5.1144
Max Act: 4.8956. Min Act: -0.1700
Data Index: 6413905 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1144. Min Range: -5.1144
Max Act: 4.8956. Min Act: -0.1700
Data Index: 4734535 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1144. Min Range: -5.1144
Max Act: 4.8956. Min Act: -0.1700
Data Index: 7616407 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1144. Min Range: -5.1144
Max Act: 4.8956. Min Act: -0.1700
Data Index: 1937694 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1144. Min Range: -5.1144
Max Act: 4.8644. Min Act: -0.1700
Data Index: 2437783 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1144. Min Range: -5.1144
Max Act: 4.9269. Min Act: -0.1700
Data Index: 1076120 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1144. Min Range: -5.1144
Max Act: 4.8644. Min Act: -0.1700
Data Index: 7519757 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1144. Min Range: -5.1144
Max Act: 4.8644. Min Act: -0.1700
Data Index: 7695411 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1144. Min Range: -5.1144
Max Act: 4.8644. Min Act: -0.1700
Data Index: 7732865 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1144. Min Range: -5.1144
Max Act: 4.8644. Min Act: -0.1700
Data Index: 8291865 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1144. Min Range: -5.1144
Max Act: 4.8331. Min Act: -0.1700
Data Index: 2861486 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #19