Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5897 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2495. Min Range: -5.2495
Max Act: 5.2495. Min Act: -0.1700
Data Index: 8262989 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2495. Min Range: -5.2495
Max Act: 5.2183. Min Act: -0.1700
Data Index: 2067575 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2495. Min Range: -5.2495
Max Act: 5.2183. Min Act: -0.1700
Data Index: 4001731 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2495. Min Range: -5.2495
Max Act: 5.2183. Min Act: -0.1700
Data Index: 7747055 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2495. Min Range: -5.2495
Max Act: 5.1870. Min Act: -0.1700
Data Index: 363427 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2495. Min Range: -5.2495
Max Act: 5.1870. Min Act: -0.1700
Data Index: 682763 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2495. Min Range: -5.2495
Max Act: 5.2183. Min Act: -0.1700
Data Index: 6145737 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2495. Min Range: -5.2495
Max Act: 5.1870. Min Act: -0.1700
Data Index: 4593647 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2495. Min Range: -5.2495
Max Act: 5.1870. Min Act: -0.1700
Data Index: 6767933 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2495. Min Range: -5.2495
Max Act: 5.1558. Min Act: -0.1700
Data Index: 7086452 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2495. Min Range: -5.2495
Max Act: 5.1558. Min Act: -0.1700
Data Index: 3259827 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2495. Min Range: -5.2495
Max Act: 5.1558. Min Act: -0.1700
Data Index: 1793431 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2495. Min Range: -5.2495
Max Act: 5.1558. Min Act: -0.1700
Data Index: 1495734 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2495. Min Range: -5.2495
Max Act: 5.1558. Min Act: -0.1700
Data Index: 34867 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2495. Min Range: -5.2495
Max Act: 5.1558. Min Act: -0.1700
Data Index: 6999013 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2495. Min Range: -5.2495
Max Act: 5.1558. Min Act: -0.1700
Data Index: 4783757 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2495. Min Range: -5.2495
Max Act: 5.1558. Min Act: -0.1700
Data Index: 8439914 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2495. Min Range: -5.2495
Max Act: 5.1558. Min Act: -0.1700
Data Index: 5424660 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2495. Min Range: -5.2495
Max Act: 5.1558. Min Act: -0.1700
Data Index: 487200 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2495. Min Range: -5.2495
Max Act: 5.1245. Min Act: -0.1700
Data Index: 2441418 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #19