Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3713 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6159. Min Range: -3.6159
Max Act: 3.6159. Min Act: -0.1700
Data Index: 832497 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6159. Min Range: -3.6159
Max Act: 3.5689. Min Act: -0.1700
Data Index: 3068879 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6159. Min Range: -3.6159
Max Act: 3.5220. Min Act: -0.1700
Data Index: 7876270 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6159. Min Range: -3.6159
Max Act: 3.4750. Min Act: -0.1700
Data Index: 4034145 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6159. Min Range: -3.6159
Max Act: 3.4750. Min Act: -0.1700
Data Index: 4638669 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6159. Min Range: -3.6159
Max Act: 3.4436. Min Act: -0.1700
Data Index: 8518191 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6159. Min Range: -3.6159
Max Act: 3.4436. Min Act: -0.1700
Data Index: 8223507 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6159. Min Range: -3.6159
Max Act: 3.4436. Min Act: -0.1700
Data Index: 3300093 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6159. Min Range: -3.6159
Max Act: 3.4280. Min Act: -0.1700
Data Index: 4205318 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6159. Min Range: -3.6159
Max Act: 3.4280. Min Act: -0.1700
Data Index: 6743965 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6159. Min Range: -3.6159
Max Act: 3.4436. Min Act: -0.1700
Data Index: 2821049 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6159. Min Range: -3.6159
Max Act: 3.4123. Min Act: -0.1700
Data Index: 5837174 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6159. Min Range: -3.6159
Max Act: 3.3966. Min Act: -0.1700
Data Index: 921337 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6159. Min Range: -3.6159
Max Act: 3.3966. Min Act: -0.1700
Data Index: 1814339 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6159. Min Range: -3.6159
Max Act: 3.3966. Min Act: -0.1700
Data Index: 1756363 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6159. Min Range: -3.6159
Max Act: 3.3966. Min Act: -0.1700
Data Index: 7240867 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6159. Min Range: -3.6159
Max Act: 3.3809. Min Act: -0.1700
Data Index: 3466732 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6159. Min Range: -3.6159
Max Act: 3.3809. Min Act: -0.1700
Data Index: 2598579 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6159. Min Range: -3.6159
Max Act: 3.3809. Min Act: -0.1700
Data Index: 1814340 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6159. Min Range: -3.6159
Max Act: 3.3652. Min Act: -0.1700
Data Index: 7431450 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #19