Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2502 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.8718. Min Range: -9.8718
Max Act: 9.8718. Min Act: -0.1700
Data Index: 3184804 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8718. Min Range: -9.8718
Max Act: 9.7468. Min Act: -0.1700
Data Index: 844282 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8718. Min Range: -9.8718
Max Act: 9.1218. Min Act: -0.1700
Data Index: 1255056 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8718. Min Range: -9.8718
Max Act: 8.9968. Min Act: -0.1700
Data Index: 219337 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8718. Min Range: -9.8718
Max Act: 9.0593. Min Act: -0.1700
Data Index: 3599523 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8718. Min Range: -9.8718
Max Act: 9.0593. Min Act: -0.1700
Data Index: 7107401 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8718. Min Range: -9.8718
Max Act: 8.7468. Min Act: -0.1700
Data Index: 8561040 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8718. Min Range: -9.8718
Max Act: 8.6843. Min Act: -0.1700
Data Index: 4569508 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8718. Min Range: -9.8718
Max Act: 8.5593. Min Act: -0.1700
Data Index: 6028819 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8718. Min Range: -9.8718
Max Act: 8.4968. Min Act: -0.1700
Data Index: 1053664 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8718. Min Range: -9.8718
Max Act: 8.4343. Min Act: -0.1700
Data Index: 891241 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8718. Min Range: -9.8718
Max Act: 8.3718. Min Act: -0.1700
Data Index: 7294903 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8718. Min Range: -9.8718
Max Act: 8.3718. Min Act: -0.1700
Data Index: 1011848 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8718. Min Range: -9.8718
Max Act: 8.3718. Min Act: -0.1700
Data Index: 2701586 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8718. Min Range: -9.8718
Max Act: 8.3093. Min Act: -0.1700
Data Index: 7835297 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8718. Min Range: -9.8718
Max Act: 8.1843. Min Act: -0.1700
Data Index: 3718415 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8718. Min Range: -9.8718
Max Act: 8.3093. Min Act: -0.1700
Data Index: 3018509 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8718. Min Range: -9.8718
Max Act: 8.2468. Min Act: -0.1700
Data Index: 2519574 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8718. Min Range: -9.8718
Max Act: 8.2468. Min Act: -0.1700
Data Index: 723495 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8718. Min Range: -9.8718
Max Act: 8.2468. Min Act: -0.1700
Data Index: 5014163 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #19