Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4064 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.6174. Min Range: -6.6174
Max Act: 6.6174. Min Act: -0.1700
Data Index: 3387083 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6174. Min Range: -6.6174
Max Act: 6.3674. Min Act: -0.1700
Data Index: 6410534 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6174. Min Range: -6.6174
Max Act: 6.0549. Min Act: -0.1700
Data Index: 731362 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6174. Min Range: -6.6174
Max Act: 6.0236. Min Act: -0.1700
Data Index: 2593683 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6174. Min Range: -6.6174
Max Act: 5.8674. Min Act: -0.1700
Data Index: 3052255 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6174. Min Range: -6.6174
Max Act: 5.8986. Min Act: -0.1700
Data Index: 2898338 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6174. Min Range: -6.6174
Max Act: 5.8986. Min Act: -0.1700
Data Index: 8555215 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6174. Min Range: -6.6174
Max Act: 5.8674. Min Act: -0.1700
Data Index: 6388855 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6174. Min Range: -6.6174
Max Act: 5.8674. Min Act: -0.1700
Data Index: 5587619 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6174. Min Range: -6.6174
Max Act: 5.8049. Min Act: -0.1700
Data Index: 5859786 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6174. Min Range: -6.6174
Max Act: 5.7736. Min Act: -0.1700
Data Index: 7041026 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6174. Min Range: -6.6174
Max Act: 5.8361. Min Act: -0.1700
Data Index: 3756931 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6174. Min Range: -6.6174
Max Act: 5.8049. Min Act: -0.1700
Data Index: 164436 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6174. Min Range: -6.6174
Max Act: 5.7736. Min Act: -0.1700
Data Index: 3904831 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6174. Min Range: -6.6174
Max Act: 5.7736. Min Act: -0.1700
Data Index: 7401962 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6174. Min Range: -6.6174
Max Act: 5.7736. Min Act: -0.1700
Data Index: 7471533 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6174. Min Range: -6.6174
Max Act: 5.7424. Min Act: -0.1700
Data Index: 6790175 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6174. Min Range: -6.6174
Max Act: 5.7424. Min Act: -0.1700
Data Index: 3124366 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6174. Min Range: -6.6174
Max Act: 5.7111. Min Act: -0.1700
Data Index: 2232031 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6174. Min Range: -6.6174
Max Act: 5.6799. Min Act: -0.1700
Data Index: 8532181 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #19