Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2659 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3441. Min Range: -6.3441
Max Act: 6.3441. Min Act: -0.1700
Data Index: 637689 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3441. Min Range: -6.3441
Max Act: 6.2191. Min Act: -0.1700
Data Index: 827855 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3441. Min Range: -6.3441
Max Act: 6.1253. Min Act: -0.1700
Data Index: 3273045 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3441. Min Range: -6.3441
Max Act: 6.0941. Min Act: -0.1700
Data Index: 564730 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3441. Min Range: -6.3441
Max Act: 6.0941. Min Act: -0.1700
Data Index: 2589114 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3441. Min Range: -6.3441
Max Act: 6.0628. Min Act: -0.1700
Data Index: 990090 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3441. Min Range: -6.3441
Max Act: 6.0003. Min Act: -0.1700
Data Index: 1960084 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3441. Min Range: -6.3441
Max Act: 6.0316. Min Act: -0.1700
Data Index: 5390005 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3441. Min Range: -6.3441
Max Act: 5.9691. Min Act: -0.1700
Data Index: 2456370 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3441. Min Range: -6.3441
Max Act: 5.9691. Min Act: -0.1700
Data Index: 7743740 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3441. Min Range: -6.3441
Max Act: 6.0003. Min Act: -0.1700
Data Index: 5740970 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3441. Min Range: -6.3441
Max Act: 5.9691. Min Act: -0.1700
Data Index: 790633 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3441. Min Range: -6.3441
Max Act: 5.9691. Min Act: -0.1700
Data Index: 8513369 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3441. Min Range: -6.3441
Max Act: 5.9378. Min Act: -0.1700
Data Index: 7410097 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3441. Min Range: -6.3441
Max Act: 5.9066. Min Act: -0.1700
Data Index: 7723139 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3441. Min Range: -6.3441
Max Act: 5.9378. Min Act: -0.1700
Data Index: 6592178 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3441. Min Range: -6.3441
Max Act: 5.9066. Min Act: -0.1700
Data Index: 2861398 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3441. Min Range: -6.3441
Max Act: 5.8441. Min Act: -0.1700
Data Index: 3709865 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3441. Min Range: -6.3441
Max Act: 5.8441. Min Act: -0.1700
Data Index: 4203010 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3441. Min Range: -6.3441
Max Act: 5.8441. Min Act: -0.1700
Data Index: 4313239 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #19