Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 352 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4749. Min Range: -6.4749
Max Act: 6.4749. Min Act: -0.1700
Data Index: 7268797 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4749. Min Range: -6.4749
Max Act: 5.8499. Min Act: -0.1700
Data Index: 6532623 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4749. Min Range: -6.4749
Max Act: 5.8187. Min Act: -0.1700
Data Index: 2675268 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4749. Min Range: -6.4749
Max Act: 5.8187. Min Act: -0.1700
Data Index: 5767444 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4749. Min Range: -6.4749
Max Act: 5.8187. Min Act: -0.1700
Data Index: 6523670 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4749. Min Range: -6.4749
Max Act: 5.8187. Min Act: -0.1700
Data Index: 8662914 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4749. Min Range: -6.4749
Max Act: 5.7874. Min Act: -0.1700
Data Index: 2700131 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4749. Min Range: -6.4749
Max Act: 5.7562. Min Act: -0.1700
Data Index: 3689166 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4749. Min Range: -6.4749
Max Act: 5.7249. Min Act: -0.1700
Data Index: 7630280 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4749. Min Range: -6.4749
Max Act: 5.6937. Min Act: -0.1700
Data Index: 5338091 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4749. Min Range: -6.4749
Max Act: 5.6312. Min Act: -0.1700
Data Index: 3131892 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4749. Min Range: -6.4749
Max Act: 5.6624. Min Act: -0.1700
Data Index: 4666014 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4749. Min Range: -6.4749
Max Act: 5.6624. Min Act: -0.1700
Data Index: 6729403 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4749. Min Range: -6.4749
Max Act: 5.5999. Min Act: -0.1700
Data Index: 6504898 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4749. Min Range: -6.4749
Max Act: 5.6312. Min Act: -0.1700
Data Index: 3426552 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4749. Min Range: -6.4749
Max Act: 5.5687. Min Act: -0.1700
Data Index: 1356645 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4749. Min Range: -6.4749
Max Act: 5.5374. Min Act: -0.1700
Data Index: 5003856 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4749. Min Range: -6.4749
Max Act: 5.5374. Min Act: -0.1700
Data Index: 7683505 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4749. Min Range: -6.4749
Max Act: 5.5062. Min Act: -0.1700
Data Index: 440871 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4749. Min Range: -6.4749
Max Act: 5.4749. Min Act: -0.1700
Data Index: 8752143 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #19