Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3334 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4827. Min Range: -4.4827
Max Act: 4.4827. Min Act: -0.1700
Data Index: 4224548 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4827. Min Range: -4.4827
Max Act: 4.2639. Min Act: -0.1700
Data Index: 5724004 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4827. Min Range: -4.4827
Max Act: 4.2014. Min Act: -0.1700
Data Index: 2538378 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4827. Min Range: -4.4827
Max Act: 4.1702. Min Act: -0.1700
Data Index: 8313772 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4827. Min Range: -4.4827
Max Act: 4.0764. Min Act: -0.1700
Data Index: 2376135 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4827. Min Range: -4.4827
Max Act: 4.0451. Min Act: -0.1700
Data Index: 2331563 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4827. Min Range: -4.4827
Max Act: 4.0451. Min Act: -0.1700
Data Index: 8313777 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4827. Min Range: -4.4827
Max Act: 3.9514. Min Act: -0.1700
Data Index: 6127916 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4827. Min Range: -4.4827
Max Act: 3.9514. Min Act: -0.1700
Data Index: 718836 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4827. Min Range: -4.4827
Max Act: 3.8888. Min Act: -0.1700
Data Index: 4633478 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4827. Min Range: -4.4827
Max Act: 3.8888. Min Act: -0.1700
Data Index: 7231764 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4827. Min Range: -4.4827
Max Act: 3.8888. Min Act: -0.1700
Data Index: 403424 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4827. Min Range: -4.4827
Max Act: 3.8263. Min Act: -0.1700
Data Index: 78681 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4827. Min Range: -4.4827
Max Act: 3.8263. Min Act: -0.1700
Data Index: 4179112 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4827. Min Range: -4.4827
Max Act: 3.8263. Min Act: -0.1700
Data Index: 2883417 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4827. Min Range: -4.4827
Max Act: 3.7950. Min Act: -0.1700
Data Index: 909055 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4827. Min Range: -4.4827
Max Act: 3.8263. Min Act: -0.1700
Data Index: 349263 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4827. Min Range: -4.4827
Max Act: 3.8263. Min Act: -0.1700
Data Index: 2308416 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4827. Min Range: -4.4827
Max Act: 3.7950. Min Act: -0.1700
Data Index: 2551856 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4827. Min Range: -4.4827
Max Act: 3.7950. Min Act: -0.1700
Data Index: 6176208 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #19