Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3453 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.0262. Min Range: -1.0262
Max Act: 1.0262. Min Act: -0.1695
Data Index: 1622257 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.0262. Min Range: -1.0262
Max Act: 1.0262. Min Act: -0.1695
Data Index: 2535352 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.0262. Min Range: -1.0262
Max Act: 1.0262. Min Act: -0.1641
Data Index: 1791006 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.0262. Min Range: -1.0262
Max Act: 1.0262. Min Act: -0.1672
Data Index: 3184720 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.0262. Min Range: -1.0262
Max Act: 0.9396. Min Act: -0.1680
Data Index: 1009204 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.0262. Min Range: -1.0262
Max Act: 0.8882. Min Act: -0.1700
Data Index: 1157057 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.0262. Min Range: -1.0262
Max Act: 0.8967. Min Act: -0.1698
Data Index: 5697733 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.0262. Min Range: -1.0262
Max Act: 0.8797. Min Act: -0.1700
Data Index: 4214023 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.0262. Min Range: -1.0262
Max Act: 0.8797. Min Act: -0.1699
Data Index: 7363958 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.0262. Min Range: -1.0262
Max Act: 0.8797. Min Act: -0.1694
Data Index: 8269095 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.0262. Min Range: -1.0262
Max Act: 0.8797. Min Act: -0.1679
Data Index: 2506202 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.0262. Min Range: -1.0262
Max Act: 0.8797. Min Act: -0.1698
Data Index: 7149911 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.0262. Min Range: -1.0262
Max Act: 0.8882. Min Act: -0.1643
Data Index: 1016869 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.0262. Min Range: -1.0262
Max Act: 0.8797. Min Act: -0.1695
Data Index: 5601386 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.0262. Min Range: -1.0262
Max Act: 0.8797. Min Act: -0.1663
Data Index: 3072472 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.0262. Min Range: -1.0262
Max Act: 0.8797. Min Act: -0.1673
Data Index: 6321123 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.0262. Min Range: -1.0262
Max Act: 0.8626. Min Act: -0.1691
Data Index: 1380090 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.0262. Min Range: -1.0262
Max Act: 0.8626. Min Act: -0.1693
Data Index: 427843 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.0262. Min Range: -1.0262
Max Act: 0.8626. Min Act: -0.1632
Data Index: 5575302 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.0262. Min Range: -1.0262
Max Act: 0.8626. Min Act: -0.1677
Data Index: 8066594 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19