Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2665 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8099. Min Range: -5.8099
Max Act: 5.8099. Min Act: -0.1700
Data Index: 2110773 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8099. Min Range: -5.8099
Max Act: 5.7786. Min Act: -0.1700
Data Index: 2660480 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8099. Min Range: -5.8099
Max Act: 5.6536. Min Act: -0.1700
Data Index: 5717761 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8099. Min Range: -5.8099
Max Act: 5.5286. Min Act: -0.1700
Data Index: 2855212 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8099. Min Range: -5.8099
Max Act: 5.4974. Min Act: -0.1700
Data Index: 5762444 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8099. Min Range: -5.8099
Max Act: 5.5286. Min Act: -0.1700
Data Index: 6170122 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8099. Min Range: -5.8099
Max Act: 5.4974. Min Act: -0.1700
Data Index: 2898950 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8099. Min Range: -5.8099
Max Act: 5.4974. Min Act: -0.1700
Data Index: 6076687 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8099. Min Range: -5.8099
Max Act: 5.4661. Min Act: -0.1700
Data Index: 7182328 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8099. Min Range: -5.8099
Max Act: 5.4349. Min Act: -0.1700
Data Index: 3542768 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8099. Min Range: -5.8099
Max Act: 5.4036. Min Act: -0.1700
Data Index: 402385 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8099. Min Range: -5.8099
Max Act: 5.4349. Min Act: -0.1700
Data Index: 507078 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8099. Min Range: -5.8099
Max Act: 5.3724. Min Act: -0.1700
Data Index: 5810762 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8099. Min Range: -5.8099
Max Act: 5.3724. Min Act: -0.1700
Data Index: 8028135 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8099. Min Range: -5.8099
Max Act: 5.4036. Min Act: -0.1700
Data Index: 3833794 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8099. Min Range: -5.8099
Max Act: 5.4036. Min Act: -0.1700
Data Index: 2002768 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8099. Min Range: -5.8099
Max Act: 5.3724. Min Act: -0.1700
Data Index: 5291309 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8099. Min Range: -5.8099
Max Act: 5.3724. Min Act: -0.1700
Data Index: 631399 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8099. Min Range: -5.8099
Max Act: 5.3724. Min Act: -0.1700
Data Index: 6396961 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8099. Min Range: -5.8099
Max Act: 5.3411. Min Act: -0.1700
Data Index: 2431912 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #19