Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2687 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4392. Min Range: -4.4392
Max Act: 4.4392. Min Act: -0.1700
Data Index: 1740161 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4392. Min Range: -4.4392
Max Act: 4.4392. Min Act: -0.1700
Data Index: 7237958 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4392. Min Range: -4.4392
Max Act: 4.4080. Min Act: -0.1700
Data Index: 2687156 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4392. Min Range: -4.4392
Max Act: 4.3767. Min Act: -0.1700
Data Index: 3940887 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4392. Min Range: -4.4392
Max Act: 4.3455. Min Act: -0.1700
Data Index: 7829781 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4392. Min Range: -4.4392
Max Act: 4.3767. Min Act: -0.1700
Data Index: 282614 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4392. Min Range: -4.4392
Max Act: 4.3455. Min Act: -0.1700
Data Index: 2146683 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4392. Min Range: -4.4392
Max Act: 4.3455. Min Act: -0.1700
Data Index: 4947991 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4392. Min Range: -4.4392
Max Act: 4.3767. Min Act: -0.1700
Data Index: 1235523 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4392. Min Range: -4.4392
Max Act: 4.3767. Min Act: -0.1700
Data Index: 3626699 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4392. Min Range: -4.4392
Max Act: 4.3455. Min Act: -0.1700
Data Index: 3580077 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4392. Min Range: -4.4392
Max Act: 4.3142. Min Act: -0.1700
Data Index: 7508131 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4392. Min Range: -4.4392
Max Act: 4.3142. Min Act: -0.1700
Data Index: 2681527 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4392. Min Range: -4.4392
Max Act: 4.3455. Min Act: -0.1700
Data Index: 2231250 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4392. Min Range: -4.4392
Max Act: 4.3455. Min Act: -0.1700
Data Index: 96823 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4392. Min Range: -4.4392
Max Act: 4.3142. Min Act: -0.1700
Data Index: 2335191 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4392. Min Range: -4.4392
Max Act: 4.3455. Min Act: -0.1700
Data Index: 1560366 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4392. Min Range: -4.4392
Max Act: 4.3455. Min Act: -0.1700
Data Index: 1385965 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4392. Min Range: -4.4392
Max Act: 4.3142. Min Act: -0.1700
Data Index: 6532507 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4392. Min Range: -4.4392
Max Act: 4.3142. Min Act: -0.1700
Data Index: 2355382 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #19