Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5092 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8583. Min Range: -3.8583
Max Act: 3.8583. Min Act: -0.1700
Data Index: 6198848 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8583. Min Range: -3.8583
Max Act: 3.7958. Min Act: -0.1700
Data Index: 543994 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8583. Min Range: -3.8583
Max Act: 3.6081. Min Act: -0.1700
Data Index: 543988 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8583. Min Range: -3.8583
Max Act: 3.5768. Min Act: -0.1700
Data Index: 543991 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8583. Min Range: -3.8583
Max Act: 3.5768. Min Act: -0.1700
Data Index: 543986 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8583. Min Range: -3.8583
Max Act: 3.5455. Min Act: -0.1700
Data Index: 543989 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8583. Min Range: -3.8583
Max Act: 3.5455. Min Act: -0.1700
Data Index: 2243905 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8583. Min Range: -3.8583
Max Act: 3.5455. Min Act: -0.1700
Data Index: 6905082 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8583. Min Range: -3.8583
Max Act: 3.5141. Min Act: -0.1700
Data Index: 2883276 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8583. Min Range: -3.8583
Max Act: 3.5141. Min Act: -0.1700
Data Index: 1907280 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8583. Min Range: -3.8583
Max Act: 3.4828. Min Act: -0.1700
Data Index: 1289589 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8583. Min Range: -3.8583
Max Act: 3.4828. Min Act: -0.1697
Data Index: 3556526 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8583. Min Range: -3.8583
Max Act: 3.4515. Min Act: -0.1700
Data Index: 2549209 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8583. Min Range: -3.8583
Max Act: 3.4515. Min Act: -0.1695
Data Index: 3556525 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8583. Min Range: -3.8583
Max Act: 3.4515. Min Act: -0.1700
Data Index: 2465914 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8583. Min Range: -3.8583
Max Act: 3.4201. Min Act: -0.1700
Data Index: 6639472 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8583. Min Range: -3.8583
Max Act: 3.3888. Min Act: -0.1700
Data Index: 6639471 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8583. Min Range: -3.8583
Max Act: 3.3888. Min Act: -0.1700
Data Index: 254081 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8583. Min Range: -3.8583
Max Act: 3.3888. Min Act: -0.1700
Data Index: 2457889 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8583. Min Range: -3.8583
Max Act: 3.3574. Min Act: -0.1700
Data Index: 2522427 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #19