Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2952 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1543. Min Range: -4.1543
Max Act: 4.1543. Min Act: -0.1700
Data Index: 4992838 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1543. Min Range: -4.1543
Max Act: 4.1230. Min Act: -0.1700
Data Index: 2000026 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1543. Min Range: -4.1543
Max Act: 4.0605. Min Act: -0.1700
Data Index: 6251078 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1543. Min Range: -4.1543
Max Act: 4.0605. Min Act: -0.1700
Data Index: 3856869 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1543. Min Range: -4.1543
Max Act: 4.0605. Min Act: -0.1700
Data Index: 2903460 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1543. Min Range: -4.1543
Max Act: 4.0293. Min Act: -0.1700
Data Index: 3856867 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1543. Min Range: -4.1543
Max Act: 4.0293. Min Act: -0.1700
Data Index: 6140526 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1543. Min Range: -4.1543
Max Act: 4.0293. Min Act: -0.1700
Data Index: 2096491 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1543. Min Range: -4.1543
Max Act: 3.9980. Min Act: -0.1700
Data Index: 6624320 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1543. Min Range: -4.1543
Max Act: 3.9980. Min Act: -0.1700
Data Index: 5912869 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1543. Min Range: -4.1543
Max Act: 3.9980. Min Act: -0.1700
Data Index: 3856872 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1543. Min Range: -4.1543
Max Act: 3.9980. Min Act: -0.1700
Data Index: 8600072 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1543. Min Range: -4.1543
Max Act: 3.9667. Min Act: -0.1700
Data Index: 4775715 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1543. Min Range: -4.1543
Max Act: 3.9667. Min Act: -0.1700
Data Index: 3856865 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1543. Min Range: -4.1543
Max Act: 3.9667. Min Act: -0.1700
Data Index: 3856868 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1543. Min Range: -4.1543
Max Act: 3.9667. Min Act: -0.1700
Data Index: 5599349 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1543. Min Range: -4.1543
Max Act: 3.9355. Min Act: -0.1700
Data Index: 3856874 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1543. Min Range: -4.1543
Max Act: 3.9667. Min Act: -0.1700
Data Index: 3639806 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1543. Min Range: -4.1543
Max Act: 3.9667. Min Act: -0.1700
Data Index: 3989394 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1543. Min Range: -4.1543
Max Act: 3.9667. Min Act: -0.1700
Data Index: 7660837 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #19