Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3625 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9519. Min Range: -7.9519
Max Act: 7.9519. Min Act: -0.1700
Data Index: 4264630 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9519. Min Range: -7.9519
Max Act: 7.8269. Min Act: -0.1700
Data Index: 7498808 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9519. Min Range: -7.9519
Max Act: 7.6394. Min Act: -0.1700
Data Index: 1096817 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9519. Min Range: -7.9519
Max Act: 7.5769. Min Act: -0.1700
Data Index: 7636583 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9519. Min Range: -7.9519
Max Act: 7.5769. Min Act: -0.1700
Data Index: 5971339 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9519. Min Range: -7.9519
Max Act: 7.5769. Min Act: -0.1700
Data Index: 1765939 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9519. Min Range: -7.9519
Max Act: 7.5144. Min Act: -0.1700
Data Index: 3897996 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9519. Min Range: -7.9519
Max Act: 7.5144. Min Act: -0.1700
Data Index: 7896773 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9519. Min Range: -7.9519
Max Act: 7.5144. Min Act: -0.1700
Data Index: 1918711 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9519. Min Range: -7.9519
Max Act: 7.5144. Min Act: -0.1700
Data Index: 8036447 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9519. Min Range: -7.9519
Max Act: 7.5144. Min Act: -0.1700
Data Index: 6197945 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9519. Min Range: -7.9519
Max Act: 7.5144. Min Act: -0.1700
Data Index: 2918994 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9519. Min Range: -7.9519
Max Act: 7.4519. Min Act: -0.1700
Data Index: 6427924 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9519. Min Range: -7.9519
Max Act: 7.4519. Min Act: -0.1700
Data Index: 8788188 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9519. Min Range: -7.9519
Max Act: 7.4519. Min Act: -0.1700
Data Index: 4039356 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9519. Min Range: -7.9519
Max Act: 7.4519. Min Act: -0.1700
Data Index: 4332062 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9519. Min Range: -7.9519
Max Act: 7.4519. Min Act: -0.1700
Data Index: 8260946 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9519. Min Range: -7.9519
Max Act: 7.4519. Min Act: -0.1700
Data Index: 7401883 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9519. Min Range: -7.9519
Max Act: 7.3894. Min Act: -0.1700
Data Index: 208849 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9519. Min Range: -7.9519
Max Act: 7.3894. Min Act: -0.1700
Data Index: 2132683 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19