Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2890 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9410. Min Range: -3.9410
Max Act: 3.9410. Min Act: -0.1700
Data Index: 7979418 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9410. Min Range: -3.9410
Max Act: 3.8472. Min Act: -0.1700
Data Index: 6822901 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9410. Min Range: -3.9410
Max Act: 3.7846. Min Act: -0.1700
Data Index: 3972293 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9410. Min Range: -3.9410
Max Act: 3.7846. Min Act: -0.1700
Data Index: 3298736 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9410. Min Range: -3.9410
Max Act: 3.7533. Min Act: -0.1700
Data Index: 7447617 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9410. Min Range: -3.9410
Max Act: 3.7533. Min Act: -0.1700
Data Index: 8446264 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9410. Min Range: -3.9410
Max Act: 3.7533. Min Act: -0.1700
Data Index: 6919973 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9410. Min Range: -3.9410
Max Act: 3.7533. Min Act: -0.1700
Data Index: 2005994 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9410. Min Range: -3.9410
Max Act: 3.7221. Min Act: -0.1700
Data Index: 7668075 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9410. Min Range: -3.9410
Max Act: 3.6908. Min Act: -0.1700
Data Index: 5786802 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9410. Min Range: -3.9410
Max Act: 3.6908. Min Act: -0.1700
Data Index: 7495270 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9410. Min Range: -3.9410
Max Act: 3.7221. Min Act: -0.1700
Data Index: 1557051 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9410. Min Range: -3.9410
Max Act: 3.6908. Min Act: -0.1700
Data Index: 4426256 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9410. Min Range: -3.9410
Max Act: 3.7221. Min Act: -0.1700
Data Index: 4245776 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9410. Min Range: -3.9410
Max Act: 3.7221. Min Act: -0.1700
Data Index: 4220141 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9410. Min Range: -3.9410
Max Act: 3.6908. Min Act: -0.1700
Data Index: 6372660 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9410. Min Range: -3.9410
Max Act: 3.7221. Min Act: -0.1700
Data Index: 3553137 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9410. Min Range: -3.9410
Max Act: 3.6595. Min Act: -0.1700
Data Index: 7045844 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9410. Min Range: -3.9410
Max Act: 3.6595. Min Act: -0.1700
Data Index: 224596 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9410. Min Range: -3.9410
Max Act: 3.6282. Min Act: -0.1700
Data Index: 1050074 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #19