Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2402 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.5525. Min Range: -2.5525
Max Act: 2.5525. Min Act: -0.1700
Data Index: 6163704 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5525. Min Range: -2.5525
Max Act: 2.5525. Min Act: -0.1700
Data Index: 6764468 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5525. Min Range: -2.5525
Max Act: 2.5040. Min Act: -0.1700
Data Index: 5756166 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5525. Min Range: -2.5525
Max Act: 2.5040. Min Act: -0.1700
Data Index: 2815257 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5525. Min Range: -2.5525
Max Act: 2.4716. Min Act: -0.1700
Data Index: 4323744 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5525. Min Range: -2.5525
Max Act: 2.4716. Min Act: -0.1700
Data Index: 2836378 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5525. Min Range: -2.5525
Max Act: 2.4390. Min Act: -0.1700
Data Index: 2894149 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5525. Min Range: -2.5525
Max Act: 2.4553. Min Act: -0.1700
Data Index: 6315986 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5525. Min Range: -2.5525
Max Act: 2.4390. Min Act: -0.1700
Data Index: 998738 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5525. Min Range: -2.5525
Max Act: 2.4390. Min Act: -0.1700
Data Index: 4025077 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5525. Min Range: -2.5525
Max Act: 2.4390. Min Act: -0.1700
Data Index: 4658646 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5525. Min Range: -2.5525
Max Act: 2.4390. Min Act: -0.1700
Data Index: 6245444 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5525. Min Range: -2.5525
Max Act: 2.4065. Min Act: -0.1700
Data Index: 1882577 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5525. Min Range: -2.5525
Max Act: 2.4065. Min Act: -0.1700
Data Index: 6067458 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5525. Min Range: -2.5525
Max Act: 2.4065. Min Act: -0.1700
Data Index: 3737530 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5525. Min Range: -2.5525
Max Act: 2.3901. Min Act: -0.1700
Data Index: 6561830 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5525. Min Range: -2.5525
Max Act: 2.3901. Min Act: -0.1700
Data Index: 5119313 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5525. Min Range: -2.5525
Max Act: 2.3738. Min Act: -0.1700
Data Index: 1296079 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5525. Min Range: -2.5525
Max Act: 2.3738. Min Act: -0.1700
Data Index: 6561760 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5525. Min Range: -2.5525
Max Act: 2.3574. Min Act: -0.1700
Data Index: 3685897 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #19