Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4443 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3556. Min Range: -3.3556
Max Act: 3.3556. Min Act: -0.1700
Data Index: 932424 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3556. Min Range: -3.3556
Max Act: 3.2457. Min Act: -0.1700
Data Index: 4957552 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3556. Min Range: -3.3556
Max Act: 3.1985. Min Act: -0.1700
Data Index: 4701179 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3556. Min Range: -3.3556
Max Act: 3.1985. Min Act: -0.1700
Data Index: 1392252 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3556. Min Range: -3.3556
Max Act: 3.1828. Min Act: -0.1700
Data Index: 8707778 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3556. Min Range: -3.3556
Max Act: 3.1513. Min Act: -0.1700
Data Index: 740126 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3556. Min Range: -3.3556
Max Act: 3.1041. Min Act: -0.1700
Data Index: 7247259 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3556. Min Range: -3.3556
Max Act: 3.0883. Min Act: -0.1700
Data Index: 732005 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3556. Min Range: -3.3556
Max Act: 3.0725. Min Act: -0.1700
Data Index: 4087682 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3556. Min Range: -3.3556
Max Act: 3.0725. Min Act: -0.1700
Data Index: 5298104 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3556. Min Range: -3.3556
Max Act: 3.0410. Min Act: -0.1700
Data Index: 3075908 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3556. Min Range: -3.3556
Max Act: 3.0410. Min Act: -0.1700
Data Index: 675335 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3556. Min Range: -3.3556
Max Act: 3.0410. Min Act: -0.1700
Data Index: 5091284 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3556. Min Range: -3.3556
Max Act: 3.0410. Min Act: -0.1700
Data Index: 7151738 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3556. Min Range: -3.3556
Max Act: 3.0410. Min Act: -0.1700
Data Index: 7469885 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3556. Min Range: -3.3556
Max Act: 3.0094. Min Act: -0.1700
Data Index: 8557446 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3556. Min Range: -3.3556
Max Act: 3.0252. Min Act: -0.1700
Data Index: 6012264 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3556. Min Range: -3.3556
Max Act: 3.0252. Min Act: -0.1700
Data Index: 4087683 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3556. Min Range: -3.3556
Max Act: 3.0094. Min Act: -0.1700
Data Index: 8659213 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3556. Min Range: -3.3556
Max Act: 3.0094. Min Act: -0.1700
Data Index: 7992788 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #19