Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 373 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.7767. Min Act: -0.1700
Data Index: 4667747 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.7298. Min Act: -0.1700
Data Index: 6830351 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.7298. Min Act: -0.1700
Data Index: 8061981 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.6985. Min Act: -0.1700
Data Index: 4107789 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.6829. Min Act: -0.1700
Data Index: 1328062 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.6516. Min Act: -0.1700
Data Index: 4056001 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.6203. Min Act: -0.1700
Data Index: 228830 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.6516. Min Act: -0.1700
Data Index: 7652895 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.6672. Min Act: -0.1700
Data Index: 3378392 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.6203. Min Act: -0.1700
Data Index: 5208955 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.6203. Min Act: -0.1700
Data Index: 8630056 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.6046. Min Act: -0.1700
Data Index: 6903036 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.5733. Min Act: -0.1700
Data Index: 5015905 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.6046. Min Act: -0.1700
Data Index: 3428900 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.5733. Min Act: -0.1700
Data Index: 300374 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.5890. Min Act: -0.1700
Data Index: 1541587 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.5890. Min Act: -0.1700
Data Index: 2358393 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.5577. Min Act: -0.1700
Data Index: 5476223 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.5577. Min Act: -0.1700
Data Index: 1648203 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.5733. Min Act: -0.1700
Data Index: 446420 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #19