Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1572 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2039. Min Range: -8.2039
Max Act: 8.2039. Min Act: -0.1700
Data Index: 6486670 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2039. Min Range: -8.2039
Max Act: 8.0789. Min Act: -0.1700
Data Index: 651560 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2039. Min Range: -8.2039
Max Act: 8.0789. Min Act: -0.1700
Data Index: 4719940 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2039. Min Range: -8.2039
Max Act: 7.9539. Min Act: -0.1700
Data Index: 5667161 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2039. Min Range: -8.2039
Max Act: 7.8289. Min Act: -0.1700
Data Index: 6183393 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2039. Min Range: -8.2039
Max Act: 7.8289. Min Act: -0.1700
Data Index: 5375872 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2039. Min Range: -8.2039
Max Act: 7.8914. Min Act: -0.1700
Data Index: 1331557 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2039. Min Range: -8.2039
Max Act: 7.8289. Min Act: -0.1700
Data Index: 4566920 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2039. Min Range: -8.2039
Max Act: 7.8289. Min Act: -0.1700
Data Index: 6977851 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2039. Min Range: -8.2039
Max Act: 7.8289. Min Act: -0.1700
Data Index: 3763343 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2039. Min Range: -8.2039
Max Act: 7.7664. Min Act: -0.1700
Data Index: 3910805 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2039. Min Range: -8.2039
Max Act: 7.7664. Min Act: -0.1700
Data Index: 3234966 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2039. Min Range: -8.2039
Max Act: 7.7664. Min Act: -0.1700
Data Index: 2907803 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2039. Min Range: -8.2039
Max Act: 7.7664. Min Act: -0.1700
Data Index: 6876183 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2039. Min Range: -8.2039
Max Act: 7.7664. Min Act: -0.1700
Data Index: 7195785 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2039. Min Range: -8.2039
Max Act: 7.7664. Min Act: -0.1700
Data Index: 6630278 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2039. Min Range: -8.2039
Max Act: 7.7039. Min Act: -0.1700
Data Index: 4074248 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2039. Min Range: -8.2039
Max Act: 7.7039. Min Act: -0.1700
Data Index: 4297720 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2039. Min Range: -8.2039
Max Act: 7.7039. Min Act: -0.1700
Data Index: 4207963 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2039. Min Range: -8.2039
Max Act: 7.6414. Min Act: -0.1700
Data Index: 2409405 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #19