Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3101 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6937. Min Range: -8.6937
Max Act: 8.6937. Min Act: -0.1700
Data Index: 7324872 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6937. Min Range: -8.6937
Max Act: 8.6312. Min Act: -0.1700
Data Index: 6622887 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6937. Min Range: -8.6937
Max Act: 8.5687. Min Act: -0.1700
Data Index: 4672111 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6937. Min Range: -8.6937
Max Act: 8.3187. Min Act: -0.1700
Data Index: 7287588 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6937. Min Range: -8.6937
Max Act: 8.3187. Min Act: -0.1700
Data Index: 2869151 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6937. Min Range: -8.6937
Max Act: 8.3187. Min Act: -0.1700
Data Index: 6786209 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6937. Min Range: -8.6937
Max Act: 8.3187. Min Act: -0.1700
Data Index: 8728273 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6937. Min Range: -8.6937
Max Act: 8.3187. Min Act: -0.1700
Data Index: 2415398 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6937. Min Range: -8.6937
Max Act: 8.3187. Min Act: -0.1700
Data Index: 7835703 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6937. Min Range: -8.6937
Max Act: 8.3187. Min Act: -0.1700
Data Index: 1866803 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6937. Min Range: -8.6937
Max Act: 8.1937. Min Act: -0.1700
Data Index: 6996271 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6937. Min Range: -8.6937
Max Act: 8.2562. Min Act: -0.1700
Data Index: 5604378 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6937. Min Range: -8.6937
Max Act: 8.2562. Min Act: -0.1700
Data Index: 3686809 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6937. Min Range: -8.6937
Max Act: 8.1937. Min Act: -0.1700
Data Index: 5002340 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6937. Min Range: -8.6937
Max Act: 8.1937. Min Act: -0.1700
Data Index: 7415751 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6937. Min Range: -8.6937
Max Act: 8.1937. Min Act: -0.1700
Data Index: 3723678 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6937. Min Range: -8.6937
Max Act: 8.1937. Min Act: -0.1700
Data Index: 2305377 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6937. Min Range: -8.6937
Max Act: 8.1937. Min Act: -0.1700
Data Index: 400458 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6937. Min Range: -8.6937
Max Act: 8.1937. Min Act: -0.1700
Data Index: 364384 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6937. Min Range: -8.6937
Max Act: 8.1937. Min Act: -0.1700
Data Index: 6838176 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #19