Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3612 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.1150. Min Range: -3.1150
Max Act: 3.1150. Min Act: -0.1700
Data Index: 4101287 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1150. Min Range: -3.1150
Max Act: 3.0519. Min Act: -0.1700
Data Index: 874833 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1150. Min Range: -3.1150
Max Act: 3.0519. Min Act: -0.1700
Data Index: 2841110 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1150. Min Range: -3.1150
Max Act: 3.0046. Min Act: -0.1700
Data Index: 4615707 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1150. Min Range: -3.1150
Max Act: 2.9729. Min Act: -0.1700
Data Index: 3807200 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1150. Min Range: -3.1150
Max Act: 2.9571. Min Act: -0.1700
Data Index: 7827878 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1150. Min Range: -3.1150
Max Act: 2.9729. Min Act: -0.1700
Data Index: 4180267 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1150. Min Range: -3.1150
Max Act: 2.9413. Min Act: -0.1700
Data Index: 1589828 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1150. Min Range: -3.1150
Max Act: 2.9413. Min Act: -0.1700
Data Index: 5065883 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1150. Min Range: -3.1150
Max Act: 2.9571. Min Act: -0.1700
Data Index: 8211153 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1150. Min Range: -3.1150
Max Act: 2.9255. Min Act: -0.1700
Data Index: 3785704 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1150. Min Range: -3.1150
Max Act: 2.8937. Min Act: -0.1700
Data Index: 7804619 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1150. Min Range: -3.1150
Max Act: 2.9096. Min Act: -0.1700
Data Index: 7031403 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1150. Min Range: -3.1150
Max Act: 2.8937. Min Act: -0.1700
Data Index: 7064614 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1150. Min Range: -3.1150
Max Act: 2.9096. Min Act: -0.1700
Data Index: 3032671 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1150. Min Range: -3.1150
Max Act: 2.8937. Min Act: -0.1700
Data Index: 3447829 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1150. Min Range: -3.1150
Max Act: 2.8779. Min Act: -0.1700
Data Index: 8589719 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1150. Min Range: -3.1150
Max Act: 2.8620. Min Act: -0.1700
Data Index: 5015760 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1150. Min Range: -3.1150
Max Act: 2.8620. Min Act: -0.1700
Data Index: 64647 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1150. Min Range: -3.1150
Max Act: 2.8779. Min Act: -0.1700
Data Index: 7546001 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #19