Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3145 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3251. Min Range: -9.3251
Max Act: 9.3251. Min Act: -0.1700
Data Index: 1540123 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3251. Min Range: -9.3251
Max Act: 8.9501. Min Act: -0.1700
Data Index: 4298847 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3251. Min Range: -9.3251
Max Act: 8.3876. Min Act: -0.1700
Data Index: 5676835 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3251. Min Range: -9.3251
Max Act: 8.2626. Min Act: -0.1700
Data Index: 2992131 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3251. Min Range: -9.3251
Max Act: 8.2314. Min Act: -0.1700
Data Index: 2992134 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3251. Min Range: -9.3251
Max Act: 8.1376. Min Act: -0.1700
Data Index: 4298840 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3251. Min Range: -9.3251
Max Act: 8.1689. Min Act: -0.1700
Data Index: 8808788 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3251. Min Range: -9.3251
Max Act: 8.1689. Min Act: -0.1700
Data Index: 837981 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3251. Min Range: -9.3251
Max Act: 8.1689. Min Act: -0.1700
Data Index: 7804973 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3251. Min Range: -9.3251
Max Act: 8.1064. Min Act: -0.1700
Data Index: 474292 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3251. Min Range: -9.3251
Max Act: 8.0751. Min Act: -0.1700
Data Index: 3880585 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3251. Min Range: -9.3251
Max Act: 8.1064. Min Act: -0.1700
Data Index: 3949308 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3251. Min Range: -9.3251
Max Act: 8.0126. Min Act: -0.1700
Data Index: 1540120 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3251. Min Range: -9.3251
Max Act: 8.0751. Min Act: -0.1700
Data Index: 4914747 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3251. Min Range: -9.3251
Max Act: 8.0439. Min Act: -0.1700
Data Index: 4665751 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3251. Min Range: -9.3251
Max Act: 8.0439. Min Act: -0.1700
Data Index: 838255 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3251. Min Range: -9.3251
Max Act: 8.0126. Min Act: -0.1700
Data Index: 5676834 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3251. Min Range: -9.3251
Max Act: 7.9814. Min Act: -0.1700
Data Index: 7662709 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3251. Min Range: -9.3251
Max Act: 8.0126. Min Act: -0.1700
Data Index: 7462033 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3251. Min Range: -9.3251
Max Act: 7.9501. Min Act: -0.1700
Data Index: 4665752 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #19