Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3569 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9794. Min Range: -8.9794
Max Act: 8.9794. Min Act: -0.1700
Data Index: 6046722 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9794. Min Range: -8.9794
Max Act: 8.7919. Min Act: -0.1700
Data Index: 7337126 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9794. Min Range: -8.9794
Max Act: 8.2919. Min Act: -0.1700
Data Index: 6819017 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9794. Min Range: -8.9794
Max Act: 8.2294. Min Act: -0.1700
Data Index: 7527713 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9794. Min Range: -8.9794
Max Act: 8.1669. Min Act: -0.1700
Data Index: 4904654 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9794. Min Range: -8.9794
Max Act: 8.1669. Min Act: -0.1700
Data Index: 5001735 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9794. Min Range: -8.9794
Max Act: 8.1044. Min Act: -0.1700
Data Index: 308776 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9794. Min Range: -8.9794
Max Act: 8.0419. Min Act: -0.1700
Data Index: 8806089 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9794. Min Range: -8.9794
Max Act: 7.9481. Min Act: -0.1700
Data Index: 7216364 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9794. Min Range: -8.9794
Max Act: 7.9481. Min Act: -0.1700
Data Index: 3505019 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9794. Min Range: -8.9794
Max Act: 7.8856. Min Act: -0.1700
Data Index: 5229530 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9794. Min Range: -8.9794
Max Act: 7.9481. Min Act: -0.1700
Data Index: 2610732 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9794. Min Range: -8.9794
Max Act: 7.8544. Min Act: -0.1700
Data Index: 8714806 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9794. Min Range: -8.9794
Max Act: 7.8544. Min Act: -0.1700
Data Index: 89141 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9794. Min Range: -8.9794
Max Act: 7.8544. Min Act: -0.1700
Data Index: 242612 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9794. Min Range: -8.9794
Max Act: 7.8231. Min Act: -0.1700
Data Index: 4771867 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9794. Min Range: -8.9794
Max Act: 7.7919. Min Act: -0.1700
Data Index: 3821136 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9794. Min Range: -8.9794
Max Act: 7.7919. Min Act: -0.1700
Data Index: 2700613 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9794. Min Range: -8.9794
Max Act: 7.7919. Min Act: -0.1700
Data Index: 4271347 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9794. Min Range: -8.9794
Max Act: 7.7919. Min Act: -0.1700
Data Index: 2570980 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #19