Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4191 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.6437. Min Range: -10.6437
Max Act: 10.6437. Min Act: -0.1700
Data Index: 5587142 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.6437. Min Range: -10.6437
Max Act: 10.5812. Min Act: -0.1700
Data Index: 269499 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.6437. Min Range: -10.6437
Max Act: 10.5187. Min Act: -0.1700
Data Index: 7457406 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.6437. Min Range: -10.6437
Max Act: 10.5187. Min Act: -0.1700
Data Index: 777958 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.6437. Min Range: -10.6437
Max Act: 10.3937. Min Act: -0.1700
Data Index: 5552128 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.6437. Min Range: -10.6437
Max Act: 10.2687. Min Act: -0.1700
Data Index: 1107912 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.6437. Min Range: -10.6437
Max Act: 10.2687. Min Act: -0.1700
Data Index: 4925807 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.6437. Min Range: -10.6437
Max Act: 10.2062. Min Act: -0.1700
Data Index: 912304 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.6437. Min Range: -10.6437
Max Act: 10.1437. Min Act: -0.1700
Data Index: 6156214 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.6437. Min Range: -10.6437
Max Act: 10.1437. Min Act: -0.1700
Data Index: 3470465 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.6437. Min Range: -10.6437
Max Act: 10.0187. Min Act: -0.1700
Data Index: 6082244 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.6437. Min Range: -10.6437
Max Act: 10.0812. Min Act: -0.1700
Data Index: 4306730 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.6437. Min Range: -10.6437
Max Act: 9.9562. Min Act: -0.1700
Data Index: 5855543 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.6437. Min Range: -10.6437
Max Act: 9.9562. Min Act: -0.1700
Data Index: 5265765 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.6437. Min Range: -10.6437
Max Act: 9.9562. Min Act: -0.1700
Data Index: 8269781 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.6437. Min Range: -10.6437
Max Act: 9.8937. Min Act: -0.1700
Data Index: 8205185 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.6437. Min Range: -10.6437
Max Act: 9.9562. Min Act: -0.1700
Data Index: 1535812 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.6437. Min Range: -10.6437
Max Act: 9.9562. Min Act: -0.1700
Data Index: 265664 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.6437. Min Range: -10.6437
Max Act: 10.0187. Min Act: -0.1700
Data Index: 1486640 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.6437. Min Range: -10.6437
Max Act: 9.9562. Min Act: -0.1700
Data Index: 6560904 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #19