Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2123 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.2474. Min Range: -10.2474
Max Act: 10.2474. Min Act: -0.1700
Data Index: 8173672 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.2474. Min Range: -10.2474
Max Act: 10.0599. Min Act: -0.1700
Data Index: 7508793 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.2474. Min Range: -10.2474
Max Act: 9.9974. Min Act: -0.1700
Data Index: 6051620 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.2474. Min Range: -10.2474
Max Act: 9.9974. Min Act: -0.1700
Data Index: 1143374 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.2474. Min Range: -10.2474
Max Act: 9.9974. Min Act: -0.1700
Data Index: 5973588 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.2474. Min Range: -10.2474
Max Act: 9.9974. Min Act: -0.1700
Data Index: 5757916 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.2474. Min Range: -10.2474
Max Act: 9.9349. Min Act: -0.1700
Data Index: 7054396 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.2474. Min Range: -10.2474
Max Act: 9.8724. Min Act: -0.1700
Data Index: 1085956 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.2474. Min Range: -10.2474
Max Act: 9.8724. Min Act: -0.1700
Data Index: 5740481 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.2474. Min Range: -10.2474
Max Act: 9.8724. Min Act: -0.1700
Data Index: 2773839 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.2474. Min Range: -10.2474
Max Act: 9.8724. Min Act: -0.1700
Data Index: 100989 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.2474. Min Range: -10.2474
Max Act: 9.8724. Min Act: -0.1700
Data Index: 794037 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.2474. Min Range: -10.2474
Max Act: 9.8724. Min Act: -0.1700
Data Index: 1981999 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.2474. Min Range: -10.2474
Max Act: 9.8099. Min Act: -0.1700
Data Index: 141086 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.2474. Min Range: -10.2474
Max Act: 9.8724. Min Act: -0.1700
Data Index: 6067325 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.2474. Min Range: -10.2474
Max Act: 9.7474. Min Act: -0.1700
Data Index: 860313 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.2474. Min Range: -10.2474
Max Act: 9.8099. Min Act: -0.1700
Data Index: 324312 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.2474. Min Range: -10.2474
Max Act: 9.8099. Min Act: -0.1700
Data Index: 794038 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.2474. Min Range: -10.2474
Max Act: 9.8099. Min Act: -0.1700
Data Index: 1389232 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.2474. Min Range: -10.2474
Max Act: 9.8099. Min Act: -0.1700
Data Index: 1777648 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #19