Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1897 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7309. Min Range: -7.7309
Max Act: 7.7309. Min Act: -0.1700
Data Index: 8342310 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7309. Min Range: -7.7309
Max Act: 7.4497. Min Act: -0.1700
Data Index: 6833158 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7309. Min Range: -7.7309
Max Act: 7.2934. Min Act: -0.1700
Data Index: 5359959 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7309. Min Range: -7.7309
Max Act: 7.2309. Min Act: -0.1700
Data Index: 4116257 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7309. Min Range: -7.7309
Max Act: 7.2309. Min Act: -0.1700
Data Index: 2369939 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7309. Min Range: -7.7309
Max Act: 7.1684. Min Act: -0.1700
Data Index: 7493787 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7309. Min Range: -7.7309
Max Act: 7.1684. Min Act: -0.1700
Data Index: 2020969 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7309. Min Range: -7.7309
Max Act: 7.1372. Min Act: -0.1700
Data Index: 609857 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7309. Min Range: -7.7309
Max Act: 7.1059. Min Act: -0.1700
Data Index: 3597674 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7309. Min Range: -7.7309
Max Act: 7.0747. Min Act: -0.1700
Data Index: 23770 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7309. Min Range: -7.7309
Max Act: 7.1059. Min Act: -0.1700
Data Index: 7477819 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7309. Min Range: -7.7309
Max Act: 7.0747. Min Act: -0.1700
Data Index: 607607 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7309. Min Range: -7.7309
Max Act: 7.0747. Min Act: -0.1700
Data Index: 8290944 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7309. Min Range: -7.7309
Max Act: 7.0434. Min Act: -0.1700
Data Index: 4277925 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7309. Min Range: -7.7309
Max Act: 7.0122. Min Act: -0.1700
Data Index: 2408295 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7309. Min Range: -7.7309
Max Act: 7.0434. Min Act: -0.1700
Data Index: 1595647 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7309. Min Range: -7.7309
Max Act: 7.0434. Min Act: -0.1700
Data Index: 83869 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7309. Min Range: -7.7309
Max Act: 6.9809. Min Act: -0.1700
Data Index: 4041865 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7309. Min Range: -7.7309
Max Act: 7.0122. Min Act: -0.1700
Data Index: 701676 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7309. Min Range: -7.7309
Max Act: 7.0122. Min Act: -0.1700
Data Index: 78265 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #19