Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2735 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8919. Min Range: -3.8919
Max Act: 3.8919. Min Act: -0.1700
Data Index: 973209 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8919. Min Range: -3.8919
Max Act: 3.8293. Min Act: -0.1700
Data Index: 1752897 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8919. Min Range: -3.8919
Max Act: 3.8293. Min Act: -0.1700
Data Index: 7574155 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8919. Min Range: -3.8919
Max Act: 3.8293. Min Act: -0.1700
Data Index: 2742631 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8919. Min Range: -3.8919
Max Act: 3.7981. Min Act: -0.1700
Data Index: 88843 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8919. Min Range: -3.8919
Max Act: 3.7981. Min Act: -0.1700
Data Index: 3566730 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8919. Min Range: -3.8919
Max Act: 3.7981. Min Act: -0.1700
Data Index: 6322596 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8919. Min Range: -3.8919
Max Act: 3.7981. Min Act: -0.1700
Data Index: 8671858 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8919. Min Range: -3.8919
Max Act: 3.7981. Min Act: -0.1700
Data Index: 8563798 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8919. Min Range: -3.8919
Max Act: 3.7981. Min Act: -0.1700
Data Index: 780914 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8919. Min Range: -3.8919
Max Act: 3.7668. Min Act: -0.1700
Data Index: 30639 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8919. Min Range: -3.8919
Max Act: 3.7668. Min Act: -0.1700
Data Index: 523197 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8919. Min Range: -3.8919
Max Act: 3.7668. Min Act: -0.1700
Data Index: 4403297 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8919. Min Range: -3.8919
Max Act: 3.7668. Min Act: -0.1700
Data Index: 7891543 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8919. Min Range: -3.8919
Max Act: 3.7668. Min Act: -0.1700
Data Index: 4195226 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8919. Min Range: -3.8919
Max Act: 3.7668. Min Act: -0.1700
Data Index: 7215076 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8919. Min Range: -3.8919
Max Act: 3.7668. Min Act: -0.1700
Data Index: 3981548 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8919. Min Range: -3.8919
Max Act: 3.7668. Min Act: -0.1700
Data Index: 3737958 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8919. Min Range: -3.8919
Max Act: 3.7668. Min Act: -0.1700
Data Index: 3097034 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8919. Min Range: -3.8919
Max Act: 3.7668. Min Act: -0.1700
Data Index: 4739899 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19