Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3803 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9964. Min Range: -4.9964
Max Act: 4.9964. Min Act: -0.1700
Data Index: 8518823 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9964. Min Range: -4.9964
Max Act: 4.9026. Min Act: -0.1700
Data Index: 3578591 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9964. Min Range: -4.9964
Max Act: 4.8401. Min Act: -0.1700
Data Index: 4751084 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9964. Min Range: -4.9964
Max Act: 4.8714. Min Act: -0.1700
Data Index: 6026115 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9964. Min Range: -4.9964
Max Act: 4.8714. Min Act: -0.1700
Data Index: 6129467 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9964. Min Range: -4.9964
Max Act: 4.8401. Min Act: -0.1700
Data Index: 4875729 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9964. Min Range: -4.9964
Max Act: 4.8089. Min Act: -0.1700
Data Index: 5546306 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9964. Min Range: -4.9964
Max Act: 4.8089. Min Act: -0.1699
Data Index: 2170339 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9964. Min Range: -4.9964
Max Act: 4.8089. Min Act: -0.1700
Data Index: 611330 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9964. Min Range: -4.9964
Max Act: 4.8089. Min Act: -0.1700
Data Index: 4557321 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9964. Min Range: -4.9964
Max Act: 4.8089. Min Act: -0.1700
Data Index: 834961 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9964. Min Range: -4.9964
Max Act: 4.7776. Min Act: -0.1700
Data Index: 843698 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9964. Min Range: -4.9964
Max Act: 4.7776. Min Act: -0.1700
Data Index: 458714 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9964. Min Range: -4.9964
Max Act: 4.7776. Min Act: -0.1700
Data Index: 689173 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9964. Min Range: -4.9964
Max Act: 4.7776. Min Act: -0.1700
Data Index: 8340349 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9964. Min Range: -4.9964
Max Act: 4.7776. Min Act: -0.1700
Data Index: 7486676 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9964. Min Range: -4.9964
Max Act: 4.7776. Min Act: -0.1700
Data Index: 6073461 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9964. Min Range: -4.9964
Max Act: 4.7776. Min Act: -0.1700
Data Index: 623957 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9964. Min Range: -4.9964
Max Act: 4.7776. Min Act: -0.1700
Data Index: 1615501 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9964. Min Range: -4.9964
Max Act: 4.7776. Min Act: -0.1700
Data Index: 3582773 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19