Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2152 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8762. Min Range: -4.8762
Max Act: 4.8762. Min Act: -0.1694
Data Index: 1701672 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8762. Min Range: -4.8762
Max Act: 4.8137. Min Act: -0.1688
Data Index: 1616365 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8762. Min Range: -4.8762
Max Act: 4.7824. Min Act: -0.1591
Data Index: 3295452 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8762. Min Range: -4.8762
Max Act: 4.8137. Min Act: -0.1700
Data Index: 6289809 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8762. Min Range: -4.8762
Max Act: 4.7824. Min Act: -0.1645
Data Index: 357191 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8762. Min Range: -4.8762
Max Act: 4.7512. Min Act: -0.1697
Data Index: 3295451 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8762. Min Range: -4.8762
Max Act: 4.7199. Min Act: -0.1692
Data Index: 6497446 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8762. Min Range: -4.8762
Max Act: 4.7199. Min Act: -0.1688
Data Index: 3622961 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8762. Min Range: -4.8762
Max Act: 4.7199. Min Act: -0.1673
Data Index: 278747 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8762. Min Range: -4.8762
Max Act: 4.6887. Min Act: -0.1700
Data Index: 6923791 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8762. Min Range: -4.8762
Max Act: 4.6887. Min Act: -0.1700
Data Index: 4927608 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8762. Min Range: -4.8762
Max Act: 4.6574. Min Act: -0.1700
Data Index: 6343367 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8762. Min Range: -4.8762
Max Act: 4.6574. Min Act: -0.1700
Data Index: 2683388 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8762. Min Range: -4.8762
Max Act: 4.6574. Min Act: -0.1628
Data Index: 5419097 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8762. Min Range: -4.8762
Max Act: 4.6574. Min Act: -0.1667
Data Index: 2051219 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8762. Min Range: -4.8762
Max Act: 4.6574. Min Act: -0.1700
Data Index: 8232983 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8762. Min Range: -4.8762
Max Act: 4.6574. Min Act: -0.1700
Data Index: 6497456 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8762. Min Range: -4.8762
Max Act: 4.6262. Min Act: -0.1681
Data Index: 5419095 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8762. Min Range: -4.8762
Max Act: 4.6574. Min Act: -0.1641
Data Index: 2275520 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8762. Min Range: -4.8762
Max Act: 4.6262. Min Act: -0.1700
Data Index: 2278329 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #19