Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2866 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3852. Min Range: -5.3852
Max Act: 5.3852. Min Act: -0.1700
Data Index: 5837237 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3852. Min Range: -5.3852
Max Act: 5.3227. Min Act: -0.1700
Data Index: 4701357 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3852. Min Range: -5.3852
Max Act: 5.2289. Min Act: -0.1700
Data Index: 6930717 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3852. Min Range: -5.3852
Max Act: 5.1977. Min Act: -0.1700
Data Index: 8452886 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3852. Min Range: -5.3852
Max Act: 5.1039. Min Act: -0.1700
Data Index: 7475520 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3852. Min Range: -5.3852
Max Act: 5.0727. Min Act: -0.1700
Data Index: 5194827 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3852. Min Range: -5.3852
Max Act: 5.0727. Min Act: -0.1700
Data Index: 1196320 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3852. Min Range: -5.3852
Max Act: 5.0727. Min Act: -0.1700
Data Index: 2051124 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3852. Min Range: -5.3852
Max Act: 5.0727. Min Act: -0.1700
Data Index: 4574318 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3852. Min Range: -5.3852
Max Act: 5.0414. Min Act: -0.1700
Data Index: 8494091 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3852. Min Range: -5.3852
Max Act: 5.0102. Min Act: -0.1700
Data Index: 4384132 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3852. Min Range: -5.3852
Max Act: 5.0102. Min Act: -0.1700
Data Index: 1078299 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3852. Min Range: -5.3852
Max Act: 4.9477. Min Act: -0.1700
Data Index: 3669495 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3852. Min Range: -5.3852
Max Act: 4.9789. Min Act: -0.1700
Data Index: 692873 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3852. Min Range: -5.3852
Max Act: 4.9789. Min Act: -0.1700
Data Index: 6458264 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3852. Min Range: -5.3852
Max Act: 4.9789. Min Act: -0.1700
Data Index: 3067660 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3852. Min Range: -5.3852
Max Act: 4.9789. Min Act: -0.1700
Data Index: 3570891 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3852. Min Range: -5.3852
Max Act: 4.9789. Min Act: -0.1700
Data Index: 5132927 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3852. Min Range: -5.3852
Max Act: 4.9477. Min Act: -0.1700
Data Index: 5548447 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3852. Min Range: -5.3852
Max Act: 5.0102. Min Act: -0.1700
Data Index: 8062950 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #19