Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 377 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 10.1468. Min Range: -10.1468
Max Act: 10.1468. Min Act: -0.1700
Data Index: 6347938 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.1468. Min Range: -10.1468
Max Act: 9.9593. Min Act: -0.1700
Data Index: 6375719 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.1468. Min Range: -10.1468
Max Act: 9.9593. Min Act: -0.1700
Data Index: 6152982 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.1468. Min Range: -10.1468
Max Act: 10.0218. Min Act: -0.1700
Data Index: 4060532 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.1468. Min Range: -10.1468
Max Act: 9.8968. Min Act: -0.1700
Data Index: 3228731 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.1468. Min Range: -10.1468
Max Act: 9.8968. Min Act: -0.1700
Data Index: 562161 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.1468. Min Range: -10.1468
Max Act: 9.8343. Min Act: -0.1700
Data Index: 3815913 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.1468. Min Range: -10.1468
Max Act: 9.8343. Min Act: -0.1700
Data Index: 530594 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.1468. Min Range: -10.1468
Max Act: 9.7718. Min Act: -0.1700
Data Index: 754435 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.1468. Min Range: -10.1468
Max Act: 9.7718. Min Act: -0.1700
Data Index: 2412179 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.1468. Min Range: -10.1468
Max Act: 9.7093. Min Act: -0.1700
Data Index: 6595149 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.1468. Min Range: -10.1468
Max Act: 9.6468. Min Act: -0.1700
Data Index: 3054679 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.1468. Min Range: -10.1468
Max Act: 9.6468. Min Act: -0.1700
Data Index: 218713 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.1468. Min Range: -10.1468
Max Act: 9.6468. Min Act: -0.1700
Data Index: 1558178 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.1468. Min Range: -10.1468
Max Act: 9.6468. Min Act: -0.1700
Data Index: 2556028 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.1468. Min Range: -10.1468
Max Act: 9.5843. Min Act: -0.1700
Data Index: 2337287 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.1468. Min Range: -10.1468
Max Act: 9.6468. Min Act: -0.1700
Data Index: 163498 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.1468. Min Range: -10.1468
Max Act: 9.5843. Min Act: -0.1700
Data Index: 3176761 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.1468. Min Range: -10.1468
Max Act: 9.5843. Min Act: -0.1700
Data Index: 6733741 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.1468. Min Range: -10.1468
Max Act: 9.5218. Min Act: -0.1700
Data Index: 259781 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #19