Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 34 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8357. Min Range: -7.8357
Max Act: 7.8357. Min Act: -0.1700
Data Index: 6999637 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8357. Min Range: -7.8357
Max Act: 7.7419. Min Act: -0.1700
Data Index: 8751348 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8357. Min Range: -7.8357
Max Act: 7.7107. Min Act: -0.1700
Data Index: 2972915 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8357. Min Range: -7.8357
Max Act: 7.6482. Min Act: -0.1700
Data Index: 1265630 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8357. Min Range: -7.8357
Max Act: 7.5544. Min Act: -0.1700
Data Index: 934139 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8357. Min Range: -7.8357
Max Act: 7.5232. Min Act: -0.1700
Data Index: 6587209 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8357. Min Range: -7.8357
Max Act: 7.4607. Min Act: -0.1700
Data Index: 5514658 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8357. Min Range: -7.8357
Max Act: 7.4294. Min Act: -0.1700
Data Index: 6152474 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8357. Min Range: -7.8357
Max Act: 7.4294. Min Act: -0.1700
Data Index: 3756048 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8357. Min Range: -7.8357
Max Act: 7.4607. Min Act: -0.1700
Data Index: 2716869 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8357. Min Range: -7.8357
Max Act: 7.3982. Min Act: -0.1700
Data Index: 7859729 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8357. Min Range: -7.8357
Max Act: 7.3357. Min Act: -0.1700
Data Index: 571738 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8357. Min Range: -7.8357
Max Act: 7.3044. Min Act: -0.1700
Data Index: 2075799 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8357. Min Range: -7.8357
Max Act: 7.2732. Min Act: -0.1700
Data Index: 4365001 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8357. Min Range: -7.8357
Max Act: 7.2419. Min Act: -0.1700
Data Index: 5076003 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8357. Min Range: -7.8357
Max Act: 7.2107. Min Act: -0.1700
Data Index: 8279519 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8357. Min Range: -7.8357
Max Act: 7.2107. Min Act: -0.1700
Data Index: 977431 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8357. Min Range: -7.8357
Max Act: 7.1794. Min Act: -0.1700
Data Index: 6958765 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8357. Min Range: -7.8357
Max Act: 7.2107. Min Act: -0.1700
Data Index: 7121653 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8357. Min Range: -7.8357
Max Act: 7.1794. Min Act: -0.1700
Data Index: 777477 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #19