Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 702 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6322. Min Range: -4.6322
Max Act: 4.6322. Min Act: -0.1700
Data Index: 4748895 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6322. Min Range: -4.6322
Max Act: 4.6009. Min Act: -0.1700
Data Index: 5783491 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6322. Min Range: -4.6322
Max Act: 4.6009. Min Act: -0.1700
Data Index: 4735218 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6322. Min Range: -4.6322
Max Act: 4.6009. Min Act: -0.1700
Data Index: 2234255 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6322. Min Range: -4.6322
Max Act: 4.5697. Min Act: -0.1700
Data Index: 4330848 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6322. Min Range: -4.6322
Max Act: 4.5697. Min Act: -0.1700
Data Index: 3611298 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6322. Min Range: -4.6322
Max Act: 4.5697. Min Act: -0.1700
Data Index: 8253869 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6322. Min Range: -4.6322
Max Act: 4.5384. Min Act: -0.1700
Data Index: 7846119 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6322. Min Range: -4.6322
Max Act: 4.5072. Min Act: -0.1700
Data Index: 3604954 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6322. Min Range: -4.6322
Max Act: 4.4759. Min Act: -0.1700
Data Index: 5055156 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6322. Min Range: -4.6322
Max Act: 4.5072. Min Act: -0.1700
Data Index: 63145 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6322. Min Range: -4.6322
Max Act: 4.4759. Min Act: -0.1700
Data Index: 1631271 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6322. Min Range: -4.6322
Max Act: 4.4759. Min Act: -0.1700
Data Index: 1794637 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6322. Min Range: -4.6322
Max Act: 4.4447. Min Act: -0.1700
Data Index: 2498200 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6322. Min Range: -4.6322
Max Act: 4.4447. Min Act: -0.1700
Data Index: 2321975 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6322. Min Range: -4.6322
Max Act: 4.4759. Min Act: -0.1700
Data Index: 568759 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6322. Min Range: -4.6322
Max Act: 4.4134. Min Act: -0.1700
Data Index: 4528961 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6322. Min Range: -4.6322
Max Act: 4.4447. Min Act: -0.1700
Data Index: 2321978 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6322. Min Range: -4.6322
Max Act: 4.4134. Min Act: -0.1700
Data Index: 1438855 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6322. Min Range: -4.6322
Max Act: 4.4134. Min Act: -0.1700
Data Index: 5044533 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #19