Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3927 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9015. Min Range: -4.9015
Max Act: 4.9015. Min Act: -0.1700
Data Index: 6362141 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9015. Min Range: -4.9015
Max Act: 4.6515. Min Act: -0.1700
Data Index: 7235702 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9015. Min Range: -4.9015
Max Act: 4.5578. Min Act: -0.1700
Data Index: 799214 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9015. Min Range: -4.9015
Max Act: 4.5265. Min Act: -0.1700
Data Index: 1869479 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9015. Min Range: -4.9015
Max Act: 4.4953. Min Act: -0.1700
Data Index: 586299 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9015. Min Range: -4.9015
Max Act: 4.4640. Min Act: -0.1700
Data Index: 3062311 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9015. Min Range: -4.9015
Max Act: 4.4328. Min Act: -0.1700
Data Index: 8629631 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9015. Min Range: -4.9015
Max Act: 4.4328. Min Act: -0.1700
Data Index: 1650416 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9015. Min Range: -4.9015
Max Act: 4.4328. Min Act: -0.1700
Data Index: 2649197 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9015. Min Range: -4.9015
Max Act: 4.4328. Min Act: -0.1700
Data Index: 3148873 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9015. Min Range: -4.9015
Max Act: 4.4328. Min Act: -0.1700
Data Index: 4689538 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9015. Min Range: -4.9015
Max Act: 4.4015. Min Act: -0.1700
Data Index: 6263603 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9015. Min Range: -4.9015
Max Act: 4.4328. Min Act: -0.1700
Data Index: 8624418 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9015. Min Range: -4.9015
Max Act: 4.3703. Min Act: -0.1700
Data Index: 6958 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9015. Min Range: -4.9015
Max Act: 4.3703. Min Act: -0.1700
Data Index: 7902533 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9015. Min Range: -4.9015
Max Act: 4.3703. Min Act: -0.1700
Data Index: 7055569 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9015. Min Range: -4.9015
Max Act: 4.3703. Min Act: -0.1700
Data Index: 6420545 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9015. Min Range: -4.9015
Max Act: 4.3703. Min Act: -0.1700
Data Index: 4637473 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9015. Min Range: -4.9015
Max Act: 4.3703. Min Act: -0.1700
Data Index: 1191287 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9015. Min Range: -4.9015
Max Act: 4.3703. Min Act: -0.1700
Data Index: 3745759 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #19