Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 46 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0626. Min Range: -4.0626
Max Act: 4.0626. Min Act: -0.1700
Data Index: 62689 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0626. Min Range: -4.0626
Max Act: 4.0313. Min Act: -0.1700
Data Index: 4105900 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0626. Min Range: -4.0626
Max Act: 4.0313. Min Act: -0.1700
Data Index: 5978504 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0626. Min Range: -4.0626
Max Act: 4.0313. Min Act: -0.1700
Data Index: 8761949 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0626. Min Range: -4.0626
Max Act: 4.0313. Min Act: -0.1700
Data Index: 7717343 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0626. Min Range: -4.0626
Max Act: 3.9688. Min Act: -0.1700
Data Index: 6884257 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0626. Min Range: -4.0626
Max Act: 3.9688. Min Act: -0.1700
Data Index: 3070575 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0626. Min Range: -4.0626
Max Act: 4.0001. Min Act: -0.1700
Data Index: 7966657 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0626. Min Range: -4.0626
Max Act: 4.0001. Min Act: -0.1700
Data Index: 927441 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0626. Min Range: -4.0626
Max Act: 4.0001. Min Act: -0.1700
Data Index: 2023539 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0626. Min Range: -4.0626
Max Act: 4.0001. Min Act: -0.1700
Data Index: 6492173 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0626. Min Range: -4.0626
Max Act: 4.0626. Min Act: -0.1700
Data Index: 2567752 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0626. Min Range: -4.0626
Max Act: 4.0001. Min Act: -0.1700
Data Index: 8730356 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0626. Min Range: -4.0626
Max Act: 3.9688. Min Act: -0.1700
Data Index: 7669822 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0626. Min Range: -4.0626
Max Act: 3.9688. Min Act: -0.1700
Data Index: 2732365 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0626. Min Range: -4.0626
Max Act: 3.9063. Min Act: -0.1700
Data Index: 7696978 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0626. Min Range: -4.0626
Max Act: 3.9688. Min Act: -0.1700
Data Index: 1139338 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0626. Min Range: -4.0626
Max Act: 3.9688. Min Act: -0.1700
Data Index: 3462922 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0626. Min Range: -4.0626
Max Act: 3.9376. Min Act: -0.1700
Data Index: 728025 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0626. Min Range: -4.0626
Max Act: 3.9688. Min Act: -0.1700
Data Index: 1851038 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #19