Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2887 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2438. Min Range: -7.2438
Max Act: 7.2438. Min Act: -0.1700
Data Index: 3942440 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2438. Min Range: -7.2438
Max Act: 7.0876. Min Act: -0.1700
Data Index: 1638400 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2438. Min Range: -7.2438
Max Act: 7.0251. Min Act: -0.1700
Data Index: 4387371 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2438. Min Range: -7.2438
Max Act: 7.0251. Min Act: -0.1700
Data Index: 3895112 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2438. Min Range: -7.2438
Max Act: 6.9938. Min Act: -0.1700
Data Index: 5226114 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2438. Min Range: -7.2438
Max Act: 6.9938. Min Act: -0.1700
Data Index: 7669855 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2438. Min Range: -7.2438
Max Act: 6.9938. Min Act: -0.1700
Data Index: 1964753 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2438. Min Range: -7.2438
Max Act: 6.9938. Min Act: -0.1700
Data Index: 924130 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2438. Min Range: -7.2438
Max Act: 6.9626. Min Act: -0.1700
Data Index: 3953578 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2438. Min Range: -7.2438
Max Act: 6.9626. Min Act: -0.1700
Data Index: 2486400 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2438. Min Range: -7.2438
Max Act: 6.9626. Min Act: -0.1700
Data Index: 213401 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2438. Min Range: -7.2438
Max Act: 6.9313. Min Act: -0.1700
Data Index: 3303095 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2438. Min Range: -7.2438
Max Act: 6.9313. Min Act: -0.1700
Data Index: 4392772 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2438. Min Range: -7.2438
Max Act: 6.9313. Min Act: -0.1700
Data Index: 1872708 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2438. Min Range: -7.2438
Max Act: 6.9626. Min Act: -0.1700
Data Index: 8435925 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2438. Min Range: -7.2438
Max Act: 6.9313. Min Act: -0.1700
Data Index: 7576455 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2438. Min Range: -7.2438
Max Act: 6.9313. Min Act: -0.1700
Data Index: 4571816 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2438. Min Range: -7.2438
Max Act: 6.9313. Min Act: -0.1700
Data Index: 4510342 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2438. Min Range: -7.2438
Max Act: 6.9313. Min Act: -0.1700
Data Index: 7829000 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2438. Min Range: -7.2438
Max Act: 6.9001. Min Act: -0.1700
Data Index: 4927294 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #19