Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2598 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5271. Min Range: -8.5271
Max Act: 8.5271. Min Act: -0.1700
Data Index: 6085164 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5271. Min Range: -8.5271
Max Act: 8.3396. Min Act: -0.1700
Data Index: 5366549 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5271. Min Range: -8.5271
Max Act: 8.3396. Min Act: -0.1700
Data Index: 8209142 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5271. Min Range: -8.5271
Max Act: 8.1521. Min Act: -0.1700
Data Index: 2069093 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5271. Min Range: -8.5271
Max Act: 8.0896. Min Act: -0.1700
Data Index: 7112384 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5271. Min Range: -8.5271
Max Act: 8.0896. Min Act: -0.1700
Data Index: 7675432 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5271. Min Range: -8.5271
Max Act: 7.8709. Min Act: -0.1700
Data Index: 259375 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5271. Min Range: -8.5271
Max Act: 7.8709. Min Act: -0.1700
Data Index: 6697448 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5271. Min Range: -8.5271
Max Act: 7.8709. Min Act: -0.1700
Data Index: 889776 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5271. Min Range: -8.5271
Max Act: 7.8084. Min Act: -0.1700
Data Index: 7848355 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5271. Min Range: -8.5271
Max Act: 7.7771. Min Act: -0.1700
Data Index: 3672026 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5271. Min Range: -8.5271
Max Act: 7.7771. Min Act: -0.1700
Data Index: 5063035 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5271. Min Range: -8.5271
Max Act: 7.7146. Min Act: -0.1700
Data Index: 7146909 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5271. Min Range: -8.5271
Max Act: 7.6521. Min Act: -0.1700
Data Index: 5151284 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5271. Min Range: -8.5271
Max Act: 7.5896. Min Act: -0.1700
Data Index: 8000515 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5271. Min Range: -8.5271
Max Act: 7.5584. Min Act: -0.1700
Data Index: 4459115 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5271. Min Range: -8.5271
Max Act: 7.5271. Min Act: -0.1700
Data Index: 7320246 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5271. Min Range: -8.5271
Max Act: 7.5271. Min Act: -0.1700
Data Index: 880322 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5271. Min Range: -8.5271
Max Act: 7.4959. Min Act: -0.1700
Data Index: 5447338 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5271. Min Range: -8.5271
Max Act: 7.4646. Min Act: -0.1700
Data Index: 139821 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #19