Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 689 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.6660. Min Range: -8.6660
Max Act: 8.6660. Min Act: -0.1700
Data Index: 2282322 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6660. Min Range: -8.6660
Max Act: 8.2910. Min Act: -0.1700
Data Index: 5612848 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6660. Min Range: -8.6660
Max Act: 8.2285. Min Act: -0.1700
Data Index: 8575302 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6660. Min Range: -8.6660
Max Act: 8.2910. Min Act: -0.1700
Data Index: 7494032 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6660. Min Range: -8.6660
Max Act: 8.0410. Min Act: -0.1700
Data Index: 2246490 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6660. Min Range: -8.6660
Max Act: 8.1035. Min Act: -0.1700
Data Index: 4850071 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6660. Min Range: -8.6660
Max Act: 7.9785. Min Act: -0.1700
Data Index: 4727192 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6660. Min Range: -8.6660
Max Act: 8.0410. Min Act: -0.1700
Data Index: 2530243 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6660. Min Range: -8.6660
Max Act: 7.9785. Min Act: -0.1700
Data Index: 7945009 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6660. Min Range: -8.6660
Max Act: 7.7910. Min Act: -0.1700
Data Index: 2274100 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6660. Min Range: -8.6660
Max Act: 7.7285. Min Act: -0.1700
Data Index: 6498141 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6660. Min Range: -8.6660
Max Act: 7.7285. Min Act: -0.1700
Data Index: 7086009 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6660. Min Range: -8.6660
Max Act: 7.7910. Min Act: -0.1700
Data Index: 638010 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6660. Min Range: -8.6660
Max Act: 7.6035. Min Act: -0.1700
Data Index: 6989961 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6660. Min Range: -8.6660
Max Act: 7.5410. Min Act: -0.1700
Data Index: 8585861 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6660. Min Range: -8.6660
Max Act: 7.6660. Min Act: -0.1700
Data Index: 2550219 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6660. Min Range: -8.6660
Max Act: 7.6660. Min Act: -0.1700
Data Index: 5528816 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6660. Min Range: -8.6660
Max Act: 7.5098. Min Act: -0.1700
Data Index: 5833687 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6660. Min Range: -8.6660
Max Act: 7.5098. Min Act: -0.1700
Data Index: 8020051 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6660. Min Range: -8.6660
Max Act: 7.4785. Min Act: -0.1700
Data Index: 3113601 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #19