Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1014 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0327. Min Range: -4.0327
Max Act: 4.0327. Min Act: -0.1700
Data Index: 1046944 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0327. Min Range: -4.0327
Max Act: 3.9702. Min Act: -0.1700
Data Index: 6125752 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0327. Min Range: -4.0327
Max Act: 3.9702. Min Act: -0.1700
Data Index: 5913405 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0327. Min Range: -4.0327
Max Act: 3.9389. Min Act: -0.1700
Data Index: 5605707 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0327. Min Range: -4.0327
Max Act: 3.9389. Min Act: -0.1700
Data Index: 5492394 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0327. Min Range: -4.0327
Max Act: 3.9076. Min Act: -0.1700
Data Index: 8528696 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0327. Min Range: -4.0327
Max Act: 3.9076. Min Act: -0.1700
Data Index: 6236205 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0327. Min Range: -4.0327
Max Act: 3.8764. Min Act: -0.1700
Data Index: 1200971 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0327. Min Range: -4.0327
Max Act: 3.8764. Min Act: -0.1700
Data Index: 1865723 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0327. Min Range: -4.0327
Max Act: 3.9076. Min Act: -0.1700
Data Index: 7940638 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0327. Min Range: -4.0327
Max Act: 3.9076. Min Act: -0.1700
Data Index: 3094938 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0327. Min Range: -4.0327
Max Act: 3.9076. Min Act: -0.1700
Data Index: 4972897 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0327. Min Range: -4.0327
Max Act: 3.9076. Min Act: -0.1700
Data Index: 2466710 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0327. Min Range: -4.0327
Max Act: 3.8451. Min Act: -0.1700
Data Index: 5717765 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0327. Min Range: -4.0327
Max Act: 3.8764. Min Act: -0.1700
Data Index: 7140307 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0327. Min Range: -4.0327
Max Act: 3.8764. Min Act: -0.1700
Data Index: 7067479 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0327. Min Range: -4.0327
Max Act: 3.8764. Min Act: -0.1700
Data Index: 3618855 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0327. Min Range: -4.0327
Max Act: 3.8764. Min Act: -0.1700
Data Index: 1008467 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0327. Min Range: -4.0327
Max Act: 3.9076. Min Act: -0.1700
Data Index: 4555666 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0327. Min Range: -4.0327
Max Act: 3.9076. Min Act: -0.1700
Data Index: 4915595 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #19