Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3900 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5718. Min Range: -6.5718
Max Act: 6.5718. Min Act: -0.1700
Data Index: 4981442 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5718. Min Range: -6.5718
Max Act: 6.5406. Min Act: -0.1700
Data Index: 7891513 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5718. Min Range: -6.5718
Max Act: 6.3843. Min Act: -0.1700
Data Index: 8648540 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5718. Min Range: -6.5718
Max Act: 6.3218. Min Act: -0.1700
Data Index: 8161142 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5718. Min Range: -6.5718
Max Act: 6.2593. Min Act: -0.1700
Data Index: 2967032 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5718. Min Range: -6.5718
Max Act: 6.2593. Min Act: -0.1700
Data Index: 3026515 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5718. Min Range: -6.5718
Max Act: 6.2281. Min Act: -0.1700
Data Index: 5980818 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5718. Min Range: -6.5718
Max Act: 6.1656. Min Act: -0.1700
Data Index: 7394841 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5718. Min Range: -6.5718
Max Act: 6.1031. Min Act: -0.1700
Data Index: 3671211 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5718. Min Range: -6.5718
Max Act: 6.1031. Min Act: -0.1700
Data Index: 3884967 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5718. Min Range: -6.5718
Max Act: 6.0406. Min Act: -0.1700
Data Index: 2836189 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5718. Min Range: -6.5718
Max Act: 6.0406. Min Act: -0.1700
Data Index: 5218770 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5718. Min Range: -6.5718
Max Act: 6.0406. Min Act: -0.1700
Data Index: 5771615 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5718. Min Range: -6.5718
Max Act: 6.0093. Min Act: -0.1700
Data Index: 4147651 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5718. Min Range: -6.5718
Max Act: 6.0093. Min Act: -0.1700
Data Index: 33908 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5718. Min Range: -6.5718
Max Act: 6.0093. Min Act: -0.1700
Data Index: 1006826 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5718. Min Range: -6.5718
Max Act: 5.9781. Min Act: -0.1700
Data Index: 6007947 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5718. Min Range: -6.5718
Max Act: 5.9781. Min Act: -0.1700
Data Index: 7755394 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5718. Min Range: -6.5718
Max Act: 5.9468. Min Act: -0.1700
Data Index: 4178996 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5718. Min Range: -6.5718
Max Act: 5.9468. Min Act: -0.1700
Data Index: 4879921 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #19