Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1704 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7337. Min Range: -4.7337
Max Act: 4.7337. Min Act: -0.1700
Data Index: 8719046 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7337. Min Range: -4.7337
Max Act: 4.3587. Min Act: -0.1700
Data Index: 497776 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7337. Min Range: -4.7337
Max Act: 4.2962. Min Act: -0.1700
Data Index: 5196553 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7337. Min Range: -4.7337
Max Act: 4.2025. Min Act: -0.1700
Data Index: 5270756 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7337. Min Range: -4.7337
Max Act: 4.2337. Min Act: -0.1700
Data Index: 2416956 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7337. Min Range: -4.7337
Max Act: 4.1399. Min Act: -0.1700
Data Index: 7355169 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7337. Min Range: -4.7337
Max Act: 4.0774. Min Act: -0.1700
Data Index: 4139518 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7337. Min Range: -4.7337
Max Act: 4.1087. Min Act: -0.1700
Data Index: 5555638 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7337. Min Range: -4.7337
Max Act: 4.1087. Min Act: -0.1700
Data Index: 6414380 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7337. Min Range: -4.7337
Max Act: 4.1087. Min Act: -0.1700
Data Index: 1373723 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7337. Min Range: -4.7337
Max Act: 4.0774. Min Act: -0.1700
Data Index: 661549 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7337. Min Range: -4.7337
Max Act: 4.0774. Min Act: -0.1700
Data Index: 2565961 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7337. Min Range: -4.7337
Max Act: 4.0462. Min Act: -0.1700
Data Index: 3720640 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7337. Min Range: -4.7337
Max Act: 4.0462. Min Act: -0.1700
Data Index: 8105294 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7337. Min Range: -4.7337
Max Act: 4.0462. Min Act: -0.1700
Data Index: 8167504 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7337. Min Range: -4.7337
Max Act: 4.0462. Min Act: -0.1700
Data Index: 8654558 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7337. Min Range: -4.7337
Max Act: 4.0149. Min Act: -0.1700
Data Index: 5338335 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7337. Min Range: -4.7337
Max Act: 4.0462. Min Act: -0.1700
Data Index: 661550 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7337. Min Range: -4.7337
Max Act: 4.0149. Min Act: -0.1700
Data Index: 2487778 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7337. Min Range: -4.7337
Max Act: 4.0149. Min Act: -0.1700
Data Index: 895862 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #19