Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3508 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9941. Min Range: -6.9941
Max Act: 6.9941. Min Act: -0.1700
Data Index: 77328 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9941. Min Range: -6.9941
Max Act: 6.8691. Min Act: -0.1700
Data Index: 3911085 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9941. Min Range: -6.9941
Max Act: 6.9004. Min Act: -0.1700
Data Index: 2283745 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9941. Min Range: -6.9941
Max Act: 6.8379. Min Act: -0.1700
Data Index: 5377487 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9941. Min Range: -6.9941
Max Act: 6.8379. Min Act: -0.1700
Data Index: 5135585 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9941. Min Range: -6.9941
Max Act: 6.8066. Min Act: -0.1700
Data Index: 2934864 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9941. Min Range: -6.9941
Max Act: 6.8066. Min Act: -0.1700
Data Index: 4359034 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9941. Min Range: -6.9941
Max Act: 6.8066. Min Act: -0.1700
Data Index: 4603434 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9941. Min Range: -6.9941
Max Act: 6.7441. Min Act: -0.1700
Data Index: 2732361 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9941. Min Range: -6.9941
Max Act: 6.7754. Min Act: -0.1700
Data Index: 4232495 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9941. Min Range: -6.9941
Max Act: 6.7441. Min Act: -0.1700
Data Index: 157877 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9941. Min Range: -6.9941
Max Act: 6.7441. Min Act: -0.1700
Data Index: 250004 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9941. Min Range: -6.9941
Max Act: 6.7441. Min Act: -0.1700
Data Index: 3522845 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9941. Min Range: -6.9941
Max Act: 6.6816. Min Act: -0.1700
Data Index: 2697099 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9941. Min Range: -6.9941
Max Act: 6.7129. Min Act: -0.1700
Data Index: 7704019 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9941. Min Range: -6.9941
Max Act: 6.7129. Min Act: -0.1700
Data Index: 8107683 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9941. Min Range: -6.9941
Max Act: 6.7129. Min Act: -0.1700
Data Index: 104907 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9941. Min Range: -6.9941
Max Act: 6.6504. Min Act: -0.1700
Data Index: 8066457 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9941. Min Range: -6.9941
Max Act: 6.7129. Min Act: -0.1700
Data Index: 5203197 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9941. Min Range: -6.9941
Max Act: 6.6816. Min Act: -0.1700
Data Index: 3234895 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #19