Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5231 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5607. Min Range: -6.5607
Max Act: 6.5607. Min Act: -0.1700
Data Index: 7836167 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5607. Min Range: -6.5607
Max Act: 6.2170. Min Act: -0.1700
Data Index: 7279570 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5607. Min Range: -6.5607
Max Act: 6.1232. Min Act: -0.1700
Data Index: 1535027 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5607. Min Range: -6.5607
Max Act: 6.1232. Min Act: -0.1700
Data Index: 8427090 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5607. Min Range: -6.5607
Max Act: 6.0920. Min Act: -0.1700
Data Index: 2888418 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5607. Min Range: -6.5607
Max Act: 6.0607. Min Act: -0.1700
Data Index: 8427089 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5607. Min Range: -6.5607
Max Act: 6.0607. Min Act: -0.1700
Data Index: 4695305 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5607. Min Range: -6.5607
Max Act: 6.0295. Min Act: -0.1700
Data Index: 1087584 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5607. Min Range: -6.5607
Max Act: 6.0607. Min Act: -0.1700
Data Index: 4815763 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5607. Min Range: -6.5607
Max Act: 6.0607. Min Act: -0.1700
Data Index: 1621938 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5607. Min Range: -6.5607
Max Act: 6.0295. Min Act: -0.1700
Data Index: 6660933 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5607. Min Range: -6.5607
Max Act: 6.0295. Min Act: -0.1700
Data Index: 950219 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5607. Min Range: -6.5607
Max Act: 6.0607. Min Act: -0.1700
Data Index: 7808447 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5607. Min Range: -6.5607
Max Act: 5.9982. Min Act: -0.1700
Data Index: 6567639 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5607. Min Range: -6.5607
Max Act: 5.9982. Min Act: -0.1700
Data Index: 6083187 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5607. Min Range: -6.5607
Max Act: 5.9982. Min Act: -0.1700
Data Index: 2758726 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5607. Min Range: -6.5607
Max Act: 5.9982. Min Act: -0.1700
Data Index: 734483 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5607. Min Range: -6.5607
Max Act: 5.9982. Min Act: -0.1700
Data Index: 3405462 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5607. Min Range: -6.5607
Max Act: 5.9982. Min Act: -0.1700
Data Index: 4867896 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5607. Min Range: -6.5607
Max Act: 5.9982. Min Act: -0.1700
Data Index: 7625166 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #19