Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6383 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1937. Min Range: -5.1937
Max Act: 5.1937. Min Act: -0.1700
Data Index: 2692893 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1937. Min Range: -5.1937
Max Act: 5.1000. Min Act: -0.1698
Data Index: 5159280 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1937. Min Range: -5.1937
Max Act: 4.8812. Min Act: -0.1700
Data Index: 4505145 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1937. Min Range: -5.1937
Max Act: 4.8500. Min Act: -0.1700
Data Index: 7811909 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1937. Min Range: -5.1937
Max Act: 4.8187. Min Act: -0.1700
Data Index: 4192175 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1937. Min Range: -5.1937
Max Act: 4.7875. Min Act: -0.1700
Data Index: 2500452 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1937. Min Range: -5.1937
Max Act: 4.7562. Min Act: -0.1700
Data Index: 2270720 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1937. Min Range: -5.1937
Max Act: 4.7562. Min Act: -0.1699
Data Index: 1986003 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1937. Min Range: -5.1937
Max Act: 4.7562. Min Act: -0.1700
Data Index: 6618050 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1937. Min Range: -5.1937
Max Act: 4.7562. Min Act: -0.1700
Data Index: 5754801 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1937. Min Range: -5.1937
Max Act: 4.7562. Min Act: -0.1700
Data Index: 4286667 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1937. Min Range: -5.1937
Max Act: 4.7250. Min Act: -0.1700
Data Index: 4434238 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1937. Min Range: -5.1937
Max Act: 4.6937. Min Act: -0.1700
Data Index: 549060 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1937. Min Range: -5.1937
Max Act: 4.7250. Min Act: -0.1700
Data Index: 5153434 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1937. Min Range: -5.1937
Max Act: 4.7250. Min Act: -0.1700
Data Index: 6936472 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1937. Min Range: -5.1937
Max Act: 4.7250. Min Act: -0.1700
Data Index: 4059142 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1937. Min Range: -5.1937
Max Act: 4.7250. Min Act: -0.1700
Data Index: 2179499 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1937. Min Range: -5.1937
Max Act: 4.6625. Min Act: -0.1700
Data Index: 6126635 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1937. Min Range: -5.1937
Max Act: 4.6625. Min Act: -0.1700
Data Index: 6251264 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1937. Min Range: -5.1937
Max Act: 4.6937. Min Act: -0.1700
Data Index: 329606 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #19