Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2137 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2368. Min Range: -3.2368
Max Act: 3.2368. Min Act: -0.1700
Data Index: 2889993 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2368. Min Range: -3.2368
Max Act: 3.2053. Min Act: -0.1700
Data Index: 1425456 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2368. Min Range: -3.2368
Max Act: 3.1424. Min Act: -0.1700
Data Index: 418086 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2368. Min Range: -3.2368
Max Act: 3.1109. Min Act: -0.1700
Data Index: 1925580 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2368. Min Range: -3.2368
Max Act: 3.1109. Min Act: -0.1700
Data Index: 8810519 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2368. Min Range: -3.2368
Max Act: 3.0794. Min Act: -0.1700
Data Index: 8105567 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2368. Min Range: -3.2368
Max Act: 3.0794. Min Act: -0.1700
Data Index: 4784321 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2368. Min Range: -3.2368
Max Act: 3.0794. Min Act: -0.1700
Data Index: 2334126 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2368. Min Range: -3.2368
Max Act: 3.0794. Min Act: -0.1700
Data Index: 4365825 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2368. Min Range: -3.2368
Max Act: 3.0794. Min Act: -0.1700
Data Index: 3804076 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2368. Min Range: -3.2368
Max Act: 3.0794. Min Act: -0.1700
Data Index: 3992056 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2368. Min Range: -3.2368
Max Act: 3.0478. Min Act: -0.1700
Data Index: 1837987 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2368. Min Range: -3.2368
Max Act: 3.0478. Min Act: -0.1700
Data Index: 4037548 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2368. Min Range: -3.2368
Max Act: 3.0478. Min Act: -0.1700
Data Index: 2652488 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2368. Min Range: -3.2368
Max Act: 3.0478. Min Act: -0.1700
Data Index: 1750305 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2368. Min Range: -3.2368
Max Act: 3.0478. Min Act: -0.1700
Data Index: 2723249 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2368. Min Range: -3.2368
Max Act: 3.0162. Min Act: -0.1700
Data Index: 1465844 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2368. Min Range: -3.2368
Max Act: 3.0162. Min Act: -0.1700
Data Index: 7723268 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2368. Min Range: -3.2368
Max Act: 3.0162. Min Act: -0.1700
Data Index: 3564787 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2368. Min Range: -3.2368
Max Act: 3.0162. Min Act: -0.1700
Data Index: 8058507 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #19