Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4639 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2959. Min Range: -5.2959
Max Act: 5.2959. Min Act: -0.1700
Data Index: 604352 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2959. Min Range: -5.2959
Max Act: 5.1709. Min Act: -0.1700
Data Index: 6636688 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2959. Min Range: -5.2959
Max Act: 5.0146. Min Act: -0.1700
Data Index: 8826469 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2959. Min Range: -5.2959
Max Act: 4.9521. Min Act: -0.1700
Data Index: 4853584 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2959. Min Range: -5.2959
Max Act: 4.9834. Min Act: -0.1700
Data Index: 717985 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2959. Min Range: -5.2959
Max Act: 4.9521. Min Act: -0.1700
Data Index: 4150904 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2959. Min Range: -5.2959
Max Act: 4.9521. Min Act: -0.1700
Data Index: 8016680 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2959. Min Range: -5.2959
Max Act: 4.9209. Min Act: -0.1700
Data Index: 4425377 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2959. Min Range: -5.2959
Max Act: 4.9209. Min Act: -0.1700
Data Index: 1150311 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2959. Min Range: -5.2959
Max Act: 4.8896. Min Act: -0.1700
Data Index: 604351 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2959. Min Range: -5.2959
Max Act: 4.8896. Min Act: -0.1700
Data Index: 6354055 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2959. Min Range: -5.2959
Max Act: 4.8584. Min Act: -0.1700
Data Index: 2279762 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2959. Min Range: -5.2959
Max Act: 4.8584. Min Act: -0.1700
Data Index: 6055857 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2959. Min Range: -5.2959
Max Act: 4.8584. Min Act: -0.1700
Data Index: 896229 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2959. Min Range: -5.2959
Max Act: 4.8896. Min Act: -0.1700
Data Index: 5997385 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2959. Min Range: -5.2959
Max Act: 4.8271. Min Act: -0.1700
Data Index: 6415545 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2959. Min Range: -5.2959
Max Act: 4.8271. Min Act: -0.1700
Data Index: 1676028 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2959. Min Range: -5.2959
Max Act: 4.7959. Min Act: -0.1700
Data Index: 6533220 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2959. Min Range: -5.2959
Max Act: 4.7959. Min Act: -0.1700
Data Index: 62899 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2959. Min Range: -5.2959
Max Act: 4.7959. Min Act: -0.1700
Data Index: 6520647 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #19