Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1783 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2081. Min Range: -5.2081
Max Act: 5.2081. Min Act: -0.1700
Data Index: 7539392 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2081. Min Range: -5.2081
Max Act: 4.7394. Min Act: -0.1700
Data Index: 1017412 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2081. Min Range: -5.2081
Max Act: 4.7706. Min Act: -0.1700
Data Index: 1234027 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2081. Min Range: -5.2081
Max Act: 4.7081. Min Act: -0.1700
Data Index: 626231 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2081. Min Range: -5.2081
Max Act: 4.7081. Min Act: -0.1700
Data Index: 4728234 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2081. Min Range: -5.2081
Max Act: 4.6456. Min Act: -0.1700
Data Index: 4541858 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2081. Min Range: -5.2081
Max Act: 4.6769. Min Act: -0.1700
Data Index: 6567699 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2081. Min Range: -5.2081
Max Act: 4.6769. Min Act: -0.1700
Data Index: 6646308 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2081. Min Range: -5.2081
Max Act: 4.6144. Min Act: -0.1700
Data Index: 6675649 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2081. Min Range: -5.2081
Max Act: 4.5206. Min Act: -0.1700
Data Index: 7975939 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2081. Min Range: -5.2081
Max Act: 4.5519. Min Act: -0.1700
Data Index: 350176 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2081. Min Range: -5.2081
Max Act: 4.5519. Min Act: -0.1700
Data Index: 7540212 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2081. Min Range: -5.2081
Max Act: 4.5519. Min Act: -0.1700
Data Index: 3558218 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2081. Min Range: -5.2081
Max Act: 4.5519. Min Act: -0.1700
Data Index: 6110988 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2081. Min Range: -5.2081
Max Act: 4.5206. Min Act: -0.1700
Data Index: 2040041 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2081. Min Range: -5.2081
Max Act: 4.4894. Min Act: -0.1700
Data Index: 3208890 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2081. Min Range: -5.2081
Max Act: 4.4894. Min Act: -0.1700
Data Index: 5328975 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2081. Min Range: -5.2081
Max Act: 4.4894. Min Act: -0.1700
Data Index: 2884505 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2081. Min Range: -5.2081
Max Act: 4.4581. Min Act: -0.1700
Data Index: 2388015 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2081. Min Range: -5.2081
Max Act: 4.4894. Min Act: -0.1700
Data Index: 1677779 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #19