Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3218 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.2267. Min Range: -2.2267
Max Act: 2.2267. Min Act: -0.1700
Data Index: 8607572 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2267. Min Range: -2.2267
Max Act: 2.2101. Min Act: -0.1700
Data Index: 4999396 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2267. Min Range: -2.2267
Max Act: 2.1769. Min Act: -0.1700
Data Index: 5492534 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2267. Min Range: -2.2267
Max Act: 2.1769. Min Act: -0.1700
Data Index: 77781 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2267. Min Range: -2.2267
Max Act: 2.1436. Min Act: -0.1700
Data Index: 7243743 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2267. Min Range: -2.2267
Max Act: 2.1436. Min Act: -0.1700
Data Index: 654345 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2267. Min Range: -2.2267
Max Act: 2.1436. Min Act: -0.1700
Data Index: 130089 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2267. Min Range: -2.2267
Max Act: 2.1436. Min Act: -0.1700
Data Index: 4999395 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2267. Min Range: -2.2267
Max Act: 2.1436. Min Act: -0.1700
Data Index: 2429896 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2267. Min Range: -2.2267
Max Act: 2.1436. Min Act: -0.1700
Data Index: 2429899 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2267. Min Range: -2.2267
Max Act: 2.1269. Min Act: -0.1700
Data Index: 8816803 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2267. Min Range: -2.2267
Max Act: 2.1269. Min Act: -0.1700
Data Index: 8607568 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2267. Min Range: -2.2267
Max Act: 2.1269. Min Act: -0.1700
Data Index: 8617869 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2267. Min Range: -2.2267
Max Act: 2.0934. Min Act: -0.1700
Data Index: 7280050 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2267. Min Range: -2.2267
Max Act: 2.0934. Min Act: -0.1700
Data Index: 5844631 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2267. Min Range: -2.2267
Max Act: 2.0934. Min Act: -0.1700
Data Index: 2370046 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2267. Min Range: -2.2267
Max Act: 2.0934. Min Act: -0.1700
Data Index: 8607570 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2267. Min Range: -2.2267
Max Act: 2.0934. Min Act: -0.1700
Data Index: 1325078 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2267. Min Range: -2.2267
Max Act: 2.0934. Min Act: -0.1700
Data Index: 130088 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2267. Min Range: -2.2267
Max Act: 2.0934. Min Act: -0.1700
Data Index: 2132594 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #19