Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2306 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4115. Min Range: -4.4115
Max Act: 4.4115. Min Act: -0.1700
Data Index: 5738682 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4115. Min Range: -4.4115
Max Act: 4.3490. Min Act: -0.1700
Data Index: 7390762 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4115. Min Range: -4.4115
Max Act: 4.3803. Min Act: -0.1700
Data Index: 4414802 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4115. Min Range: -4.4115
Max Act: 4.3490. Min Act: -0.1700
Data Index: 6506053 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4115. Min Range: -4.4115
Max Act: 4.3490. Min Act: -0.1700
Data Index: 5418392 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4115. Min Range: -4.4115
Max Act: 4.3178. Min Act: -0.1700
Data Index: 1111831 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4115. Min Range: -4.4115
Max Act: 4.3490. Min Act: -0.1700
Data Index: 3838955 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4115. Min Range: -4.4115
Max Act: 4.3490. Min Act: -0.1700
Data Index: 8513759 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4115. Min Range: -4.4115
Max Act: 4.3178. Min Act: -0.1700
Data Index: 5055872 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4115. Min Range: -4.4115
Max Act: 4.3178. Min Act: -0.1700
Data Index: 3378545 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4115. Min Range: -4.4115
Max Act: 4.3178. Min Act: -0.1700
Data Index: 7358940 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4115. Min Range: -4.4115
Max Act: 4.3178. Min Act: -0.1700
Data Index: 5468660 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4115. Min Range: -4.4115
Max Act: 4.3490. Min Act: -0.1700
Data Index: 3704476 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4115. Min Range: -4.4115
Max Act: 4.3178. Min Act: -0.1700
Data Index: 1999435 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4115. Min Range: -4.4115
Max Act: 4.3178. Min Act: -0.1700
Data Index: 3884078 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4115. Min Range: -4.4115
Max Act: 4.2553. Min Act: -0.1700
Data Index: 5251398 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4115. Min Range: -4.4115
Max Act: 4.2865. Min Act: -0.1700
Data Index: 7479917 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4115. Min Range: -4.4115
Max Act: 4.2865. Min Act: -0.1700
Data Index: 5163529 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4115. Min Range: -4.4115
Max Act: 4.2865. Min Act: -0.1700
Data Index: 1840822 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4115. Min Range: -4.4115
Max Act: 4.2553. Min Act: -0.1700
Data Index: 2562768 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #19