Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3647 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8278. Min Range: -6.8278
Max Act: 6.8278. Min Act: -0.1700
Data Index: 2597728 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8278. Min Range: -6.8278
Max Act: 6.7653. Min Act: -0.1700
Data Index: 2495298 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8278. Min Range: -6.8278
Max Act: 6.7653. Min Act: -0.1700
Data Index: 2502932 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8278. Min Range: -6.8278
Max Act: 6.7653. Min Act: -0.1700
Data Index: 1864523 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8278. Min Range: -6.8278
Max Act: 6.7028. Min Act: -0.1700
Data Index: 4020902 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8278. Min Range: -6.8278
Max Act: 6.7028. Min Act: -0.1700
Data Index: 7545002 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8278. Min Range: -6.8278
Max Act: 6.7028. Min Act: -0.1700
Data Index: 2331474 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8278. Min Range: -6.8278
Max Act: 6.7028. Min Act: -0.1700
Data Index: 2523676 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8278. Min Range: -6.8278
Max Act: 6.7028. Min Act: -0.1700
Data Index: 7635375 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8278. Min Range: -6.8278
Max Act: 6.6716. Min Act: -0.1700
Data Index: 1456260 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8278. Min Range: -6.8278
Max Act: 6.6091. Min Act: -0.1700
Data Index: 7129760 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8278. Min Range: -6.8278
Max Act: 6.5778. Min Act: -0.1700
Data Index: 7278761 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8278. Min Range: -6.8278
Max Act: 6.5778. Min Act: -0.1700
Data Index: 3819142 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8278. Min Range: -6.8278
Max Act: 6.6091. Min Act: -0.1700
Data Index: 759643 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8278. Min Range: -6.8278
Max Act: 6.5778. Min Act: -0.1700
Data Index: 6326727 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8278. Min Range: -6.8278
Max Act: 6.6091. Min Act: -0.1700
Data Index: 7617638 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8278. Min Range: -6.8278
Max Act: 6.6091. Min Act: -0.1700
Data Index: 7072029 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8278. Min Range: -6.8278
Max Act: 6.5778. Min Act: -0.1700
Data Index: 8525802 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8278. Min Range: -6.8278
Max Act: 6.5466. Min Act: -0.1700
Data Index: 1248896 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8278. Min Range: -6.8278
Max Act: 6.5466. Min Act: -0.1700
Data Index: 3220148 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #19