Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2784 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0511. Min Range: -5.0511
Max Act: 5.0511. Min Act: -0.1700
Data Index: 7263319 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0511. Min Range: -5.0511
Max Act: 4.8949. Min Act: -0.1700
Data Index: 3306930 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0511. Min Range: -5.0511
Max Act: 4.8949. Min Act: -0.1700
Data Index: 4051480 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0511. Min Range: -5.0511
Max Act: 4.8636. Min Act: -0.1700
Data Index: 7933395 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0511. Min Range: -5.0511
Max Act: 4.8324. Min Act: -0.1700
Data Index: 2847079 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0511. Min Range: -5.0511
Max Act: 4.8324. Min Act: -0.1700
Data Index: 8621047 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0511. Min Range: -5.0511
Max Act: 4.8011. Min Act: -0.1700
Data Index: 3959851 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0511. Min Range: -5.0511
Max Act: 4.7699. Min Act: -0.1700
Data Index: 7612477 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0511. Min Range: -5.0511
Max Act: 4.7699. Min Act: -0.1700
Data Index: 7263320 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0511. Min Range: -5.0511
Max Act: 4.7699. Min Act: -0.1700
Data Index: 7950427 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0511. Min Range: -5.0511
Max Act: 4.7386. Min Act: -0.1700
Data Index: 280320 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0511. Min Range: -5.0511
Max Act: 4.7386. Min Act: -0.1700
Data Index: 770091 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0511. Min Range: -5.0511
Max Act: 4.7386. Min Act: -0.1700
Data Index: 214415 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0511. Min Range: -5.0511
Max Act: 4.7386. Min Act: -0.1700
Data Index: 5913098 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0511. Min Range: -5.0511
Max Act: 4.6761. Min Act: -0.1700
Data Index: 7063393 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0511. Min Range: -5.0511
Max Act: 4.7074. Min Act: -0.1700
Data Index: 4780386 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0511. Min Range: -5.0511
Max Act: 4.7074. Min Act: -0.1700
Data Index: 771636 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0511. Min Range: -5.0511
Max Act: 4.7074. Min Act: -0.1700
Data Index: 609013 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0511. Min Range: -5.0511
Max Act: 4.7386. Min Act: -0.1700
Data Index: 2732071 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0511. Min Range: -5.0511
Max Act: 4.6761. Min Act: -0.1700
Data Index: 2738918 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19