Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3279 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5074. Min Range: -4.5074
Max Act: 4.5074. Min Act: -0.1700
Data Index: 133779 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5074. Min Range: -4.5074
Max Act: 4.4762. Min Act: -0.1700
Data Index: 7429982 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5074. Min Range: -4.5074
Max Act: 4.4449. Min Act: -0.1700
Data Index: 1883359 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5074. Min Range: -4.5074
Max Act: 4.4449. Min Act: -0.1700
Data Index: 3661840 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5074. Min Range: -4.5074
Max Act: 4.4137. Min Act: -0.1700
Data Index: 8597701 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5074. Min Range: -4.5074
Max Act: 4.3512. Min Act: -0.1700
Data Index: 2108886 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5074. Min Range: -4.5074
Max Act: 4.2887. Min Act: -0.1700
Data Index: 197255 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5074. Min Range: -4.5074
Max Act: 4.2262. Min Act: -0.1700
Data Index: 5218511 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5074. Min Range: -4.5074
Max Act: 4.1949. Min Act: -0.1700
Data Index: 921986 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5074. Min Range: -4.5074
Max Act: 4.1949. Min Act: -0.1700
Data Index: 330878 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5074. Min Range: -4.5074
Max Act: 4.1949. Min Act: -0.1700
Data Index: 4122286 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5074. Min Range: -4.5074
Max Act: 4.1949. Min Act: -0.1700
Data Index: 4218722 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5074. Min Range: -4.5074
Max Act: 4.1324. Min Act: -0.1700
Data Index: 4286889 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5074. Min Range: -4.5074
Max Act: 4.1324. Min Act: -0.1700
Data Index: 4512231 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5074. Min Range: -4.5074
Max Act: 4.1637. Min Act: -0.1700
Data Index: 7413007 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5074. Min Range: -4.5074
Max Act: 4.1637. Min Act: -0.1700
Data Index: 4585342 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5074. Min Range: -4.5074
Max Act: 4.1637. Min Act: -0.1700
Data Index: 1838689 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5074. Min Range: -4.5074
Max Act: 4.1324. Min Act: -0.1700
Data Index: 2148312 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5074. Min Range: -4.5074
Max Act: 4.1324. Min Act: -0.1700
Data Index: 5790836 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5074. Min Range: -4.5074
Max Act: 4.1637. Min Act: -0.1700
Data Index: 7308260 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #19