Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1273 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.7137. Min Range: -7.7137
Max Act: 7.7137. Min Act: -0.1700
Data Index: 4574882 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7137. Min Range: -7.7137
Max Act: 7.6512. Min Act: -0.1700
Data Index: 5846161 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7137. Min Range: -7.7137
Max Act: 7.6825. Min Act: -0.1700
Data Index: 8392478 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7137. Min Range: -7.7137
Max Act: 7.6825. Min Act: -0.1700
Data Index: 4626393 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7137. Min Range: -7.7137
Max Act: 7.6200. Min Act: -0.1700
Data Index: 6944273 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7137. Min Range: -7.7137
Max Act: 7.6200. Min Act: -0.1700
Data Index: 2357315 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7137. Min Range: -7.7137
Max Act: 7.4950. Min Act: -0.1700
Data Index: 4934695 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7137. Min Range: -7.7137
Max Act: 7.4637. Min Act: -0.1700
Data Index: 505159 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7137. Min Range: -7.7137
Max Act: 7.4950. Min Act: -0.1700
Data Index: 4679097 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7137. Min Range: -7.7137
Max Act: 7.4637. Min Act: -0.1700
Data Index: 2422717 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7137. Min Range: -7.7137
Max Act: 7.4012. Min Act: -0.1700
Data Index: 4522345 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7137. Min Range: -7.7137
Max Act: 7.4637. Min Act: -0.1700
Data Index: 8614835 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7137. Min Range: -7.7137
Max Act: 7.3387. Min Act: -0.1700
Data Index: 435445 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7137. Min Range: -7.7137
Max Act: 7.4325. Min Act: -0.1700
Data Index: 3695517 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7137. Min Range: -7.7137
Max Act: 7.4012. Min Act: -0.1700
Data Index: 6655269 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7137. Min Range: -7.7137
Max Act: 7.3700. Min Act: -0.1700
Data Index: 4306794 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7137. Min Range: -7.7137
Max Act: 7.3387. Min Act: -0.1700
Data Index: 4425799 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7137. Min Range: -7.7137
Max Act: 7.3387. Min Act: -0.1700
Data Index: 5749852 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7137. Min Range: -7.7137
Max Act: 7.3387. Min Act: -0.1700
Data Index: 7238142 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7137. Min Range: -7.7137
Max Act: 7.3387. Min Act: -0.1700
Data Index: 5789111 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #19