Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3322 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4529. Min Range: -6.4529
Max Act: 6.4216. Min Act: -0.1700
Data Index: 105656 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4529. Min Range: -6.4529
Max Act: 6.4216. Min Act: -0.1700
Data Index: 5686960 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4529. Min Range: -6.4529
Max Act: 6.4529. Min Act: -0.1700
Data Index: 1573446 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4529. Min Range: -6.4529
Max Act: 6.3591. Min Act: -0.1700
Data Index: 7042553 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4529. Min Range: -6.4529
Max Act: 6.3591. Min Act: -0.1700
Data Index: 5468027 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4529. Min Range: -6.4529
Max Act: 6.2966. Min Act: -0.1700
Data Index: 2820692 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4529. Min Range: -6.4529
Max Act: 6.2654. Min Act: -0.1700
Data Index: 419224 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4529. Min Range: -6.4529
Max Act: 6.2029. Min Act: -0.1700
Data Index: 8482966 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4529. Min Range: -6.4529
Max Act: 6.1716. Min Act: -0.1700
Data Index: 3014948 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4529. Min Range: -6.4529
Max Act: 6.1716. Min Act: -0.1700
Data Index: 7169643 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4529. Min Range: -6.4529
Max Act: 6.1404. Min Act: -0.1700
Data Index: 3240585 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4529. Min Range: -6.4529
Max Act: 6.1404. Min Act: -0.1700
Data Index: 4500073 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4529. Min Range: -6.4529
Max Act: 6.1091. Min Act: -0.1700
Data Index: 1070092 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4529. Min Range: -6.4529
Max Act: 6.1091. Min Act: -0.1700
Data Index: 2812960 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4529. Min Range: -6.4529
Max Act: 6.0466. Min Act: -0.1700
Data Index: 3719280 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4529. Min Range: -6.4529
Max Act: 6.0779. Min Act: -0.1700
Data Index: 84144 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4529. Min Range: -6.4529
Max Act: 6.0466. Min Act: -0.1700
Data Index: 8779479 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4529. Min Range: -6.4529
Max Act: 6.0779. Min Act: -0.1700
Data Index: 2111934 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4529. Min Range: -6.4529
Max Act: 6.0466. Min Act: -0.1700
Data Index: 7331572 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4529. Min Range: -6.4529
Max Act: 6.0154. Min Act: -0.1700
Data Index: 5980590 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #19