Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3258 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.8119. Min Range: -2.8119
Max Act: 2.8119. Min Act: -0.1700
Data Index: 4095334 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8119. Min Range: -2.8119
Max Act: 2.6200. Min Act: -0.1700
Data Index: 7424691 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8119. Min Range: -2.8119
Max Act: 2.5879. Min Act: -0.1700
Data Index: 819452 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8119. Min Range: -2.8119
Max Act: 2.5717. Min Act: -0.1700
Data Index: 8148514 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8119. Min Range: -2.8119
Max Act: 2.5879. Min Act: -0.1700
Data Index: 5489780 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8119. Min Range: -2.8119
Max Act: 2.5717. Min Act: -0.1700
Data Index: 4768849 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8119. Min Range: -2.8119
Max Act: 2.5556. Min Act: -0.1700
Data Index: 1743242 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8119. Min Range: -2.8119
Max Act: 2.5556. Min Act: -0.1700
Data Index: 3918097 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8119. Min Range: -2.8119
Max Act: 2.5395. Min Act: -0.1700
Data Index: 4992552 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8119. Min Range: -2.8119
Max Act: 2.5556. Min Act: -0.1700
Data Index: 5335016 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8119. Min Range: -2.8119
Max Act: 2.5556. Min Act: -0.1700
Data Index: 2950626 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8119. Min Range: -2.8119
Max Act: 2.5395. Min Act: -0.1700
Data Index: 8149009 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8119. Min Range: -2.8119
Max Act: 2.5556. Min Act: -0.1700
Data Index: 2395896 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8119. Min Range: -2.8119
Max Act: 2.5395. Min Act: -0.1700
Data Index: 5487956 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8119. Min Range: -2.8119
Max Act: 2.5395. Min Act: -0.1700
Data Index: 4515190 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8119. Min Range: -2.8119
Max Act: 2.5233. Min Act: -0.1700
Data Index: 2428535 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8119. Min Range: -2.8119
Max Act: 2.5395. Min Act: -0.1700
Data Index: 4330376 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8119. Min Range: -2.8119
Max Act: 2.5071. Min Act: -0.1700
Data Index: 1977804 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8119. Min Range: -2.8119
Max Act: 2.5071. Min Act: -0.1700
Data Index: 1319089 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8119. Min Range: -2.8119
Max Act: 2.5071. Min Act: -0.1700
Data Index: 6150851 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #19