Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4046 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2476. Min Range: -3.2476
Max Act: 3.2476. Min Act: -0.1700
Data Index: 592004 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2476. Min Range: -3.2476
Max Act: 3.1218. Min Act: -0.1700
Data Index: 6783215 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2476. Min Range: -3.2476
Max Act: 3.1218. Min Act: -0.1700
Data Index: 2319292 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2476. Min Range: -3.2476
Max Act: 3.1060. Min Act: -0.1700
Data Index: 4410034 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2476. Min Range: -3.2476
Max Act: 3.1060. Min Act: -0.1700
Data Index: 454521 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2476. Min Range: -3.2476
Max Act: 3.1060. Min Act: -0.1700
Data Index: 6238250 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2476. Min Range: -3.2476
Max Act: 3.1060. Min Act: -0.1700
Data Index: 3853472 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2476. Min Range: -3.2476
Max Act: 3.1060. Min Act: -0.1700
Data Index: 6201107 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2476. Min Range: -3.2476
Max Act: 3.1060. Min Act: -0.1700
Data Index: 943664 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2476. Min Range: -3.2476
Max Act: 3.1060. Min Act: -0.1700
Data Index: 5643944 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2476. Min Range: -3.2476
Max Act: 3.0745. Min Act: -0.1700
Data Index: 6473216 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2476. Min Range: -3.2476
Max Act: 3.0745. Min Act: -0.1700
Data Index: 7667726 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2476. Min Range: -3.2476
Max Act: 3.0745. Min Act: -0.1700
Data Index: 6206229 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2476. Min Range: -3.2476
Max Act: 3.0902. Min Act: -0.1700
Data Index: 1732527 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2476. Min Range: -3.2476
Max Act: 3.0902. Min Act: -0.1700
Data Index: 8786105 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2476. Min Range: -3.2476
Max Act: 3.0745. Min Act: -0.1700
Data Index: 7261082 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2476. Min Range: -3.2476
Max Act: 3.0745. Min Act: -0.1700
Data Index: 2144966 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2476. Min Range: -3.2476
Max Act: 3.0745. Min Act: -0.1700
Data Index: 256612 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2476. Min Range: -3.2476
Max Act: 3.0745. Min Act: -0.1700
Data Index: 6560615 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2476. Min Range: -3.2476
Max Act: 3.0902. Min Act: -0.1700
Data Index: 1581671 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #19