Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 889 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9673. Min Range: -7.9673
Max Act: 7.9673. Min Act: -0.1700
Data Index: 2670929 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9673. Min Range: -7.9673
Max Act: 7.8423. Min Act: -0.1700
Data Index: 8281191 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9673. Min Range: -7.9673
Max Act: 7.8110. Min Act: -0.1700
Data Index: 3438036 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9673. Min Range: -7.9673
Max Act: 7.6548. Min Act: -0.1700
Data Index: 7565925 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9673. Min Range: -7.9673
Max Act: 7.5298. Min Act: -0.1700
Data Index: 81332 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9673. Min Range: -7.9673
Max Act: 7.4360. Min Act: -0.1700
Data Index: 6108443 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9673. Min Range: -7.9673
Max Act: 7.4360. Min Act: -0.1700
Data Index: 3217330 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9673. Min Range: -7.9673
Max Act: 7.4048. Min Act: -0.1700
Data Index: 8031703 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9673. Min Range: -7.9673
Max Act: 7.3735. Min Act: -0.1700
Data Index: 7245007 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9673. Min Range: -7.9673
Max Act: 7.3110. Min Act: -0.1700
Data Index: 6010854 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9673. Min Range: -7.9673
Max Act: 7.3110. Min Act: -0.1700
Data Index: 6015228 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9673. Min Range: -7.9673
Max Act: 7.2798. Min Act: -0.1700
Data Index: 8161371 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9673. Min Range: -7.9673
Max Act: 7.2485. Min Act: -0.1700
Data Index: 3181408 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9673. Min Range: -7.9673
Max Act: 7.2485. Min Act: -0.1700
Data Index: 4083750 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9673. Min Range: -7.9673
Max Act: 7.2173. Min Act: -0.1700
Data Index: 5161430 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9673. Min Range: -7.9673
Max Act: 7.1860. Min Act: -0.1700
Data Index: 3806578 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9673. Min Range: -7.9673
Max Act: 7.1860. Min Act: -0.1700
Data Index: 6949140 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9673. Min Range: -7.9673
Max Act: 7.1860. Min Act: -0.1700
Data Index: 6368386 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9673. Min Range: -7.9673
Max Act: 7.1860. Min Act: -0.1700
Data Index: 6119940 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9673. Min Range: -7.9673
Max Act: 7.1860. Min Act: -0.1700
Data Index: 3020887 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #19