Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3233 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2126. Min Range: -7.2126
Max Act: 7.2126. Min Act: -0.1700
Data Index: 1695056 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2126. Min Range: -7.2126
Max Act: 7.1188. Min Act: -0.1700
Data Index: 5457277 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2126. Min Range: -7.2126
Max Act: 6.9938. Min Act: -0.1700
Data Index: 1627004 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2126. Min Range: -7.2126
Max Act: 6.9626. Min Act: -0.1700
Data Index: 2014181 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2126. Min Range: -7.2126
Max Act: 6.9001. Min Act: -0.1700
Data Index: 2128106 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2126. Min Range: -7.2126
Max Act: 6.8688. Min Act: -0.1700
Data Index: 234627 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2126. Min Range: -7.2126
Max Act: 6.8688. Min Act: -0.1700
Data Index: 7043990 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2126. Min Range: -7.2126
Max Act: 6.8063. Min Act: -0.1700
Data Index: 4929142 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2126. Min Range: -7.2126
Max Act: 6.7751. Min Act: -0.1700
Data Index: 6051357 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2126. Min Range: -7.2126
Max Act: 6.7751. Min Act: -0.1700
Data Index: 4005791 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2126. Min Range: -7.2126
Max Act: 6.7126. Min Act: -0.1700
Data Index: 8606679 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2126. Min Range: -7.2126
Max Act: 6.7126. Min Act: -0.1700
Data Index: 2899450 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2126. Min Range: -7.2126
Max Act: 6.7126. Min Act: -0.1700
Data Index: 7900583 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2126. Min Range: -7.2126
Max Act: 6.6813. Min Act: -0.1700
Data Index: 1548525 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2126. Min Range: -7.2126
Max Act: 6.6501. Min Act: -0.1700
Data Index: 295732 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2126. Min Range: -7.2126
Max Act: 6.5876. Min Act: -0.1700
Data Index: 5296210 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2126. Min Range: -7.2126
Max Act: 6.5876. Min Act: -0.1700
Data Index: 5438774 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2126. Min Range: -7.2126
Max Act: 6.5563. Min Act: -0.1700
Data Index: 697781 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2126. Min Range: -7.2126
Max Act: 6.5563. Min Act: -0.1700
Data Index: 6809250 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2126. Min Range: -7.2126
Max Act: 6.5251. Min Act: -0.1700
Data Index: 1195465 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #19