Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2379 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8502. Min Range: -3.8502
Max Act: 3.8502. Min Act: -0.1700
Data Index: 1248236 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8502. Min Range: -3.8502
Max Act: 3.7877. Min Act: -0.1700
Data Index: 8262636 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8502. Min Range: -3.8502
Max Act: 3.7564. Min Act: -0.1700
Data Index: 3527186 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8502. Min Range: -3.8502
Max Act: 3.7564. Min Act: -0.1700
Data Index: 6087151 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8502. Min Range: -3.8502
Max Act: 3.7251. Min Act: -0.1700
Data Index: 6361668 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8502. Min Range: -3.8502
Max Act: 3.7251. Min Act: -0.1700
Data Index: 2968769 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8502. Min Range: -3.8502
Max Act: 3.6938. Min Act: -0.1700
Data Index: 2085612 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8502. Min Range: -3.8502
Max Act: 3.6938. Min Act: -0.1700
Data Index: 8715829 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8502. Min Range: -3.8502
Max Act: 3.6625. Min Act: -0.1700
Data Index: 4640933 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8502. Min Range: -3.8502
Max Act: 3.6625. Min Act: -0.1700
Data Index: 3296435 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8502. Min Range: -3.8502
Max Act: 3.6625. Min Act: -0.1700
Data Index: 7796762 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8502. Min Range: -3.8502
Max Act: 3.6625. Min Act: -0.1700
Data Index: 6200737 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8502. Min Range: -3.8502
Max Act: 3.6312. Min Act: -0.1700
Data Index: 7768195 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8502. Min Range: -3.8502
Max Act: 3.6312. Min Act: -0.1700
Data Index: 1748296 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8502. Min Range: -3.8502
Max Act: 3.6312. Min Act: -0.1700
Data Index: 6031118 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8502. Min Range: -3.8502
Max Act: 3.6312. Min Act: -0.1700
Data Index: 2780722 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8502. Min Range: -3.8502
Max Act: 3.5999. Min Act: -0.1700
Data Index: 7377302 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8502. Min Range: -3.8502
Max Act: 3.5999. Min Act: -0.1700
Data Index: 6682894 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8502. Min Range: -3.8502
Max Act: 3.5686. Min Act: -0.1700
Data Index: 2645056 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8502. Min Range: -3.8502
Max Act: 3.5686. Min Act: -0.1700
Data Index: 4392196 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19