Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 608 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4955. Min Range: -3.4955
Max Act: 3.4955. Min Act: -0.1700
Data Index: 4977974 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4955. Min Range: -3.4955
Max Act: 3.4955. Min Act: -0.1700
Data Index: 972624 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4955. Min Range: -3.4955
Max Act: 3.4955. Min Act: -0.1700
Data Index: 3599345 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4955. Min Range: -3.4955
Max Act: 3.4642. Min Act: -0.1700
Data Index: 7378569 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4955. Min Range: -3.4955
Max Act: 3.4642. Min Act: -0.1700
Data Index: 2869037 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4955. Min Range: -3.4955
Max Act: 3.4642. Min Act: -0.1700
Data Index: 178385 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4955. Min Range: -3.4955
Max Act: 3.4329. Min Act: -0.1700
Data Index: 7791726 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4955. Min Range: -3.4955
Max Act: 3.4329. Min Act: -0.1700
Data Index: 2390883 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4955. Min Range: -3.4955
Max Act: 3.4642. Min Act: -0.1700
Data Index: 2161048 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4955. Min Range: -3.4955
Max Act: 3.4642. Min Act: -0.1700
Data Index: 6486851 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4955. Min Range: -3.4955
Max Act: 3.4642. Min Act: -0.1700
Data Index: 816811 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4955. Min Range: -3.4955
Max Act: 3.4642. Min Act: -0.1700
Data Index: 5988900 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4955. Min Range: -3.4955
Max Act: 3.4642. Min Act: -0.1700
Data Index: 5815176 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4955. Min Range: -3.4955
Max Act: 3.4642. Min Act: -0.1700
Data Index: 1708891 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4955. Min Range: -3.4955
Max Act: 3.4642. Min Act: -0.1700
Data Index: 5383142 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4955. Min Range: -3.4955
Max Act: 3.4329. Min Act: -0.1700
Data Index: 5128308 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4955. Min Range: -3.4955
Max Act: 3.4329. Min Act: -0.1700
Data Index: 997009 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4955. Min Range: -3.4955
Max Act: 3.4329. Min Act: -0.1700
Data Index: 2767810 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4955. Min Range: -3.4955
Max Act: 3.4329. Min Act: -0.1700
Data Index: 1114383 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4955. Min Range: -3.4955
Max Act: 3.4329. Min Act: -0.1700
Data Index: 3026327 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19