Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2828 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0694. Min Range: -6.0694
Max Act: 6.0382. Min Act: -0.1700
Data Index: 2635964 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0694. Min Range: -6.0694
Max Act: 6.0694. Min Act: -0.1700
Data Index: 3243928 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0694. Min Range: -6.0694
Max Act: 6.0069. Min Act: -0.1700
Data Index: 7933197 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0694. Min Range: -6.0694
Max Act: 5.8819. Min Act: -0.1700
Data Index: 8680960 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0694. Min Range: -6.0694
Max Act: 5.8819. Min Act: -0.1700
Data Index: 2588320 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0694. Min Range: -6.0694
Max Act: 5.8194. Min Act: -0.1700
Data Index: 8288925 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0694. Min Range: -6.0694
Max Act: 5.7882. Min Act: -0.1700
Data Index: 126238 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0694. Min Range: -6.0694
Max Act: 5.7569. Min Act: -0.1700
Data Index: 4973022 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0694. Min Range: -6.0694
Max Act: 5.7257. Min Act: -0.1700
Data Index: 4488988 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0694. Min Range: -6.0694
Max Act: 5.7257. Min Act: -0.1700
Data Index: 3066452 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0694. Min Range: -6.0694
Max Act: 5.7257. Min Act: -0.1700
Data Index: 421755 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0694. Min Range: -6.0694
Max Act: 5.6944. Min Act: -0.1700
Data Index: 5738625 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0694. Min Range: -6.0694
Max Act: 5.6944. Min Act: -0.1700
Data Index: 5098750 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0694. Min Range: -6.0694
Max Act: 5.6944. Min Act: -0.1700
Data Index: 6911024 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0694. Min Range: -6.0694
Max Act: 5.6632. Min Act: -0.1700
Data Index: 2399865 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0694. Min Range: -6.0694
Max Act: 5.6632. Min Act: -0.1700
Data Index: 3417769 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0694. Min Range: -6.0694
Max Act: 5.6632. Min Act: -0.1700
Data Index: 1225237 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0694. Min Range: -6.0694
Max Act: 5.6632. Min Act: -0.1700
Data Index: 4865954 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0694. Min Range: -6.0694
Max Act: 5.6319. Min Act: -0.1700
Data Index: 1841205 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0694. Min Range: -6.0694
Max Act: 5.6632. Min Act: -0.1700
Data Index: 5833839 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #19