Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2001 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.0075. Min Range: -2.0075
Max Act: 2.0075. Min Act: -0.1700
Data Index: 6112229 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0075. Min Range: -2.0075
Max Act: 1.9991. Min Act: -0.1693
Data Index: 8282851 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0075. Min Range: -2.0075
Max Act: 1.9991. Min Act: -0.1700
Data Index: 4001880 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0075. Min Range: -2.0075
Max Act: 1.9822. Min Act: -0.1700
Data Index: 1705523 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0075. Min Range: -2.0075
Max Act: 1.9822. Min Act: -0.1700
Data Index: 1491018 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0075. Min Range: -2.0075
Max Act: 1.9737. Min Act: -0.1675
Data Index: 2469040 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0075. Min Range: -2.0075
Max Act: 1.9568. Min Act: -0.1700
Data Index: 3543218 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0075. Min Range: -2.0075
Max Act: 1.9398. Min Act: -0.1699
Data Index: 8042117 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0075. Min Range: -2.0075
Max Act: 1.9398. Min Act: -0.1700
Data Index: 5774832 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0075. Min Range: -2.0075
Max Act: 1.9398. Min Act: -0.1700
Data Index: 4279674 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0075. Min Range: -2.0075
Max Act: 1.9398. Min Act: -0.1700
Data Index: 1625824 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0075. Min Range: -2.0075
Max Act: 1.9228. Min Act: -0.1700
Data Index: 5442698 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0075. Min Range: -2.0075
Max Act: 1.9313. Min Act: -0.1700
Data Index: 5392949 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0075. Min Range: -2.0075
Max Act: 1.9228. Min Act: -0.1700
Data Index: 7816968 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0075. Min Range: -2.0075
Max Act: 1.9313. Min Act: -0.1699
Data Index: 8438129 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0075. Min Range: -2.0075
Max Act: 1.9398. Min Act: -0.1699
Data Index: 3867694 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0075. Min Range: -2.0075
Max Act: 1.9228. Min Act: -0.1700
Data Index: 2711044 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0075. Min Range: -2.0075
Max Act: 1.9143. Min Act: -0.1700
Data Index: 4320170 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0075. Min Range: -2.0075
Max Act: 1.9228. Min Act: -0.1700
Data Index: 4001882 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0075. Min Range: -2.0075
Max Act: 1.9143. Min Act: -0.1699
Data Index: 5943640 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #19