Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2755 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9938. Min Range: -5.9938
Max Act: 5.9938. Min Act: -0.1700
Data Index: 1743543 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9938. Min Range: -5.9938
Max Act: 5.9000. Min Act: -0.1700
Data Index: 7873615 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9938. Min Range: -5.9938
Max Act: 5.7438. Min Act: -0.1700
Data Index: 2170673 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9938. Min Range: -5.9938
Max Act: 5.6500. Min Act: -0.1700
Data Index: 8515860 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9938. Min Range: -5.9938
Max Act: 5.6813. Min Act: -0.1700
Data Index: 1256147 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9938. Min Range: -5.9938
Max Act: 5.6500. Min Act: -0.1700
Data Index: 8788370 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9938. Min Range: -5.9938
Max Act: 5.6500. Min Act: -0.1700
Data Index: 5105175 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9938. Min Range: -5.9938
Max Act: 5.5563. Min Act: -0.1700
Data Index: 6192017 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9938. Min Range: -5.9938
Max Act: 5.5875. Min Act: -0.1700
Data Index: 5678056 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9938. Min Range: -5.9938
Max Act: 5.5875. Min Act: -0.1700
Data Index: 32152 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9938. Min Range: -5.9938
Max Act: 5.5563. Min Act: -0.1700
Data Index: 2106932 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9938. Min Range: -5.9938
Max Act: 5.5250. Min Act: -0.1700
Data Index: 7475155 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9938. Min Range: -5.9938
Max Act: 5.4938. Min Act: -0.1700
Data Index: 849240 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9938. Min Range: -5.9938
Max Act: 5.5250. Min Act: -0.1700
Data Index: 2898260 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9938. Min Range: -5.9938
Max Act: 5.5250. Min Act: -0.1700
Data Index: 7343653 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9938. Min Range: -5.9938
Max Act: 5.5250. Min Act: -0.1700
Data Index: 1187270 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9938. Min Range: -5.9938
Max Act: 5.5250. Min Act: -0.1700
Data Index: 346915 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9938. Min Range: -5.9938
Max Act: 5.5250. Min Act: -0.1700
Data Index: 8744949 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9938. Min Range: -5.9938
Max Act: 5.4625. Min Act: -0.1700
Data Index: 177754 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9938. Min Range: -5.9938
Max Act: 5.5250. Min Act: -0.1700
Data Index: 2890426 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #19