Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2478 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9988. Min Range: -2.9988
Max Act: 2.9988. Min Act: -0.1700
Data Index: 3157851 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9988. Min Range: -2.9988
Max Act: 2.9672. Min Act: -0.1700
Data Index: 2949210 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9988. Min Range: -2.9988
Max Act: 2.8880. Min Act: -0.1700
Data Index: 2033115 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9988. Min Range: -2.9988
Max Act: 2.8880. Min Act: -0.1700
Data Index: 2986493 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9988. Min Range: -2.9988
Max Act: 2.8880. Min Act: -0.1700
Data Index: 830854 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9988. Min Range: -2.9988
Max Act: 2.8721. Min Act: -0.1700
Data Index: 2324907 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9988. Min Range: -2.9988
Max Act: 2.8721. Min Act: -0.1700
Data Index: 5961055 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9988. Min Range: -2.9988
Max Act: 2.8403. Min Act: -0.1700
Data Index: 4518313 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9988. Min Range: -2.9988
Max Act: 2.8403. Min Act: -0.1700
Data Index: 4775429 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9988. Min Range: -2.9988
Max Act: 2.8244. Min Act: -0.1700
Data Index: 3744895 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9988. Min Range: -2.9988
Max Act: 2.8085. Min Act: -0.1700
Data Index: 5052132 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9988. Min Range: -2.9988
Max Act: 2.8085. Min Act: -0.1700
Data Index: 3749834 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9988. Min Range: -2.9988
Max Act: 2.7926. Min Act: -0.1700
Data Index: 1130420 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9988. Min Range: -2.9988
Max Act: 2.8085. Min Act: -0.1700
Data Index: 3252184 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9988. Min Range: -2.9988
Max Act: 2.7926. Min Act: -0.1700
Data Index: 3763354 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9988. Min Range: -2.9988
Max Act: 2.7926. Min Act: -0.1700
Data Index: 2874484 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9988. Min Range: -2.9988
Max Act: 2.7926. Min Act: -0.1700
Data Index: 5293268 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9988. Min Range: -2.9988
Max Act: 2.7767. Min Act: -0.1700
Data Index: 770976 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9988. Min Range: -2.9988
Max Act: 2.7767. Min Act: -0.1700
Data Index: 1411453 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9988. Min Range: -2.9988
Max Act: 2.7767. Min Act: -0.1700
Data Index: 1220523 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #19