Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 732 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1188. Min Range: -6.1188
Max Act: 6.1188. Min Act: -0.1700
Data Index: 7665420 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1188. Min Range: -6.1188
Max Act: 5.5875. Min Act: -0.1700
Data Index: 2330006 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1188. Min Range: -6.1188
Max Act: 5.5563. Min Act: -0.1700
Data Index: 7032691 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1188. Min Range: -6.1188
Max Act: 5.4938. Min Act: -0.1700
Data Index: 5535943 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1188. Min Range: -6.1188
Max Act: 5.4625. Min Act: -0.1700
Data Index: 5139305 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1188. Min Range: -6.1188
Max Act: 5.4625. Min Act: -0.1700
Data Index: 4268770 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1188. Min Range: -6.1188
Max Act: 5.4625. Min Act: -0.1700
Data Index: 1178600 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1188. Min Range: -6.1188
Max Act: 5.4313. Min Act: -0.1700
Data Index: 6283605 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1188. Min Range: -6.1188
Max Act: 5.4000. Min Act: -0.1700
Data Index: 7971093 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1188. Min Range: -6.1188
Max Act: 5.4000. Min Act: -0.1700
Data Index: 4088892 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1188. Min Range: -6.1188
Max Act: 5.3688. Min Act: -0.1700
Data Index: 4165882 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1188. Min Range: -6.1188
Max Act: 5.3688. Min Act: -0.1700
Data Index: 8295557 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1188. Min Range: -6.1188
Max Act: 5.3688. Min Act: -0.1700
Data Index: 346299 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1188. Min Range: -6.1188
Max Act: 5.3063. Min Act: -0.1700
Data Index: 2315764 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1188. Min Range: -6.1188
Max Act: 5.2750. Min Act: -0.1700
Data Index: 847837 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1188. Min Range: -6.1188
Max Act: 5.2750. Min Act: -0.1700
Data Index: 7803901 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1188. Min Range: -6.1188
Max Act: 5.2750. Min Act: -0.1700
Data Index: 7882499 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1188. Min Range: -6.1188
Max Act: 5.3063. Min Act: -0.1700
Data Index: 2564724 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1188. Min Range: -6.1188
Max Act: 5.2438. Min Act: -0.1700
Data Index: 6490793 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1188. Min Range: -6.1188
Max Act: 5.2750. Min Act: -0.1700
Data Index: 3851882 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #19