Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 49 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.2859. Min Range: -6.2859
Max Act: 6.2859. Min Act: -0.1700
Data Index: 3608321 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2859. Min Range: -6.2859
Max Act: 6.1609. Min Act: -0.1700
Data Index: 8557232 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2859. Min Range: -6.2859
Max Act: 6.1609. Min Act: -0.1700
Data Index: 5712916 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2859. Min Range: -6.2859
Max Act: 6.1609. Min Act: -0.1700
Data Index: 7210095 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2859. Min Range: -6.2859
Max Act: 6.1609. Min Act: -0.1700
Data Index: 4857105 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2859. Min Range: -6.2859
Max Act: 6.1609. Min Act: -0.1687
Data Index: 7093686 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2859. Min Range: -6.2859
Max Act: 6.1609. Min Act: -0.1626
Data Index: 6832243 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2859. Min Range: -6.2859
Max Act: 6.1297. Min Act: -0.1700
Data Index: 570541 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2859. Min Range: -6.2859
Max Act: 6.1297. Min Act: -0.1700
Data Index: 6493613 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2859. Min Range: -6.2859
Max Act: 6.1297. Min Act: -0.1700
Data Index: 2921671 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2859. Min Range: -6.2859
Max Act: 6.0984. Min Act: -0.1700
Data Index: 22990 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2859. Min Range: -6.2859
Max Act: 6.0984. Min Act: -0.1700
Data Index: 6427203 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2859. Min Range: -6.2859
Max Act: 6.0672. Min Act: -0.1700
Data Index: 1514352 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2859. Min Range: -6.2859
Max Act: 6.0047. Min Act: -0.1700
Data Index: 5631933 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2859. Min Range: -6.2859
Max Act: 6.0047. Min Act: -0.1700
Data Index: 3365695 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2859. Min Range: -6.2859
Max Act: 5.9734. Min Act: -0.1700
Data Index: 6179060 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2859. Min Range: -6.2859
Max Act: 6.0047. Min Act: -0.1683
Data Index: 6191906 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2859. Min Range: -6.2859
Max Act: 6.0047. Min Act: -0.1700
Data Index: 227524 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2859. Min Range: -6.2859
Max Act: 6.0047. Min Act: -0.1700
Data Index: 1986947 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2859. Min Range: -6.2859
Max Act: 6.0047. Min Act: -0.1698
Data Index: 911096 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #19