Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4196 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0944. Min Range: -6.0944
Max Act: 6.0944. Min Act: -0.1700
Data Index: 4478832 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0944. Min Range: -6.0944
Max Act: 6.0631. Min Act: -0.1700
Data Index: 3420401 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0944. Min Range: -6.0944
Max Act: 5.9694. Min Act: -0.1700
Data Index: 3090039 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0944. Min Range: -6.0944
Max Act: 5.8756. Min Act: -0.1700
Data Index: 4577501 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0944. Min Range: -6.0944
Max Act: 5.8444. Min Act: -0.1700
Data Index: 7586201 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0944. Min Range: -6.0944
Max Act: 5.8131. Min Act: -0.1700
Data Index: 5925153 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0944. Min Range: -6.0944
Max Act: 5.8131. Min Act: -0.1700
Data Index: 857718 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0944. Min Range: -6.0944
Max Act: 5.7819. Min Act: -0.1700
Data Index: 1228029 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0944. Min Range: -6.0944
Max Act: 5.7819. Min Act: -0.1700
Data Index: 5607798 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0944. Min Range: -6.0944
Max Act: 5.8131. Min Act: -0.1700
Data Index: 8648361 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0944. Min Range: -6.0944
Max Act: 5.7819. Min Act: -0.1700
Data Index: 496263 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0944. Min Range: -6.0944
Max Act: 5.7819. Min Act: -0.1700
Data Index: 4017395 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0944. Min Range: -6.0944
Max Act: 5.7506. Min Act: -0.1700
Data Index: 4477854 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0944. Min Range: -6.0944
Max Act: 5.7194. Min Act: -0.1700
Data Index: 1015919 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0944. Min Range: -6.0944
Max Act: 5.7506. Min Act: -0.1700
Data Index: 53038 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0944. Min Range: -6.0944
Max Act: 5.7194. Min Act: -0.1700
Data Index: 8284320 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0944. Min Range: -6.0944
Max Act: 5.7194. Min Act: -0.1700
Data Index: 5362595 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0944. Min Range: -6.0944
Max Act: 5.6569. Min Act: -0.1700
Data Index: 1052710 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0944. Min Range: -6.0944
Max Act: 5.6569. Min Act: -0.1700
Data Index: 6777225 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0944. Min Range: -6.0944
Max Act: 5.6569. Min Act: -0.1700
Data Index: 605340 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #19