Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4113 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5014. Min Range: -5.5014
Max Act: 5.5014. Min Act: -0.1700
Data Index: 6918439 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5014. Min Range: -5.5014
Max Act: 5.1264. Min Act: -0.1700
Data Index: 6106818 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5014. Min Range: -5.5014
Max Act: 5.0952. Min Act: -0.1700
Data Index: 6918438 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5014. Min Range: -5.5014
Max Act: 5.0952. Min Act: -0.1700
Data Index: 6939672 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5014. Min Range: -5.5014
Max Act: 5.0639. Min Act: -0.1700
Data Index: 1376100 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5014. Min Range: -5.5014
Max Act: 5.0639. Min Act: -0.1700
Data Index: 5023230 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5014. Min Range: -5.5014
Max Act: 5.0327. Min Act: -0.1700
Data Index: 5841923 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5014. Min Range: -5.5014
Max Act: 5.0639. Min Act: -0.1700
Data Index: 2562907 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5014. Min Range: -5.5014
Max Act: 5.0014. Min Act: -0.1700
Data Index: 165506 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5014. Min Range: -5.5014
Max Act: 4.9702. Min Act: -0.1700
Data Index: 5566573 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5014. Min Range: -5.5014
Max Act: 4.9389. Min Act: -0.1700
Data Index: 165496 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5014. Min Range: -5.5014
Max Act: 4.8452. Min Act: -0.1700
Data Index: 8479049 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5014. Min Range: -5.5014
Max Act: 4.8452. Min Act: -0.1700
Data Index: 1376098 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5014. Min Range: -5.5014
Max Act: 4.8452. Min Act: -0.1700
Data Index: 6918431 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5014. Min Range: -5.5014
Max Act: 4.8452. Min Act: -0.1700
Data Index: 3658363 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5014. Min Range: -5.5014
Max Act: 4.8139. Min Act: -0.1700
Data Index: 8479045 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5014. Min Range: -5.5014
Max Act: 4.8139. Min Act: -0.1700
Data Index: 3658355 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5014. Min Range: -5.5014
Max Act: 4.7827. Min Act: -0.1700
Data Index: 4538090 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5014. Min Range: -5.5014
Max Act: 4.7827. Min Act: -0.1700
Data Index: 3658360 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5014. Min Range: -5.5014
Max Act: 4.7827. Min Act: -0.1700
Data Index: 1589448 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #19