Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2698 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.7099. Min Range: -6.7099
Max Act: 6.7099. Min Act: -0.1700
Data Index: 3255444 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7099. Min Range: -6.7099
Max Act: 6.7099. Min Act: -0.1700
Data Index: 1254360 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7099. Min Range: -6.7099
Max Act: 6.6474. Min Act: -0.1700
Data Index: 7052854 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7099. Min Range: -6.7099
Max Act: 6.6161. Min Act: -0.1700
Data Index: 2653658 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7099. Min Range: -6.7099
Max Act: 6.5849. Min Act: -0.1700
Data Index: 443235 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7099. Min Range: -6.7099
Max Act: 6.5536. Min Act: -0.1700
Data Index: 2786329 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7099. Min Range: -6.7099
Max Act: 6.5224. Min Act: -0.1700
Data Index: 4112700 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7099. Min Range: -6.7099
Max Act: 6.4911. Min Act: -0.1700
Data Index: 5678472 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7099. Min Range: -6.7099
Max Act: 6.4911. Min Act: -0.1700
Data Index: 1325529 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7099. Min Range: -6.7099
Max Act: 6.4599. Min Act: -0.1700
Data Index: 2109501 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7099. Min Range: -6.7099
Max Act: 6.4286. Min Act: -0.1700
Data Index: 2899646 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7099. Min Range: -6.7099
Max Act: 6.4286. Min Act: -0.1700
Data Index: 7376224 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7099. Min Range: -6.7099
Max Act: 6.3974. Min Act: -0.1700
Data Index: 8520541 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7099. Min Range: -6.7099
Max Act: 6.4286. Min Act: -0.1700
Data Index: 2402093 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7099. Min Range: -6.7099
Max Act: 6.3349. Min Act: -0.1700
Data Index: 2834244 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7099. Min Range: -6.7099
Max Act: 6.3974. Min Act: -0.1700
Data Index: 5408648 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7099. Min Range: -6.7099
Max Act: 6.3349. Min Act: -0.1700
Data Index: 8452921 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7099. Min Range: -6.7099
Max Act: 6.3349. Min Act: -0.1700
Data Index: 8020698 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7099. Min Range: -6.7099
Max Act: 6.2724. Min Act: -0.1700
Data Index: 1481970 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7099. Min Range: -6.7099
Max Act: 6.2724. Min Act: -0.1700
Data Index: 4052300 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #19