Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1253 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.6029. Min Range: -1.6029
Max Act: 1.6029. Min Act: -0.1673
Data Index: 558880 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6029. Min Range: -1.6029
Max Act: 1.5941. Min Act: -0.1652
Data Index: 4430442 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6029. Min Range: -1.6029
Max Act: 1.5941. Min Act: -0.1700
Data Index: 908819 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6029. Min Range: -1.6029
Max Act: 1.5941. Min Act: -0.1700
Data Index: 7548012 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6029. Min Range: -1.6029
Max Act: 1.5767. Min Act: -0.1546
Data Index: 4927142 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6029. Min Range: -1.6029
Max Act: 1.5767. Min Act: -0.1303
Data Index: 5143447 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6029. Min Range: -1.6029
Max Act: 1.5679. Min Act: -0.1589
Data Index: 4609789 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6029. Min Range: -1.6029
Max Act: 1.5679. Min Act: -0.1465
Data Index: 2643835 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6029. Min Range: -1.6029
Max Act: 1.5592. Min Act: -0.1636
Data Index: 7676641 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6029. Min Range: -1.6029
Max Act: 1.5592. Min Act: -0.1692
Data Index: 1786816 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6029. Min Range: -1.6029
Max Act: 1.5679. Min Act: -0.1679
Data Index: 342230 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6029. Min Range: -1.6029
Max Act: 1.5592. Min Act: -0.1691
Data Index: 5535311 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6029. Min Range: -1.6029
Max Act: 1.5592. Min Act: -0.1698
Data Index: 3474469 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6029. Min Range: -1.6029
Max Act: 1.5592. Min Act: -0.1692
Data Index: 333284 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6029. Min Range: -1.6029
Max Act: 1.5592. Min Act: -0.1671
Data Index: 5907112 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6029. Min Range: -1.6029
Max Act: 1.5504. Min Act: -0.1616
Data Index: 3030662 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6029. Min Range: -1.6029
Max Act: 1.5504. Min Act: -0.1681
Data Index: 6760987 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6029. Min Range: -1.6029
Max Act: 1.5504. Min Act: -0.1700
Data Index: 2826321 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6029. Min Range: -1.6029
Max Act: 1.5504. Min Act: -0.1699
Data Index: 5760675 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6029. Min Range: -1.6029
Max Act: 1.5592. Min Act: -0.1643
Data Index: 3737205 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19