Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5373 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1544. Min Range: -5.1544
Max Act: 5.1544. Min Act: -0.1700
Data Index: 7005058 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1544. Min Range: -5.1544
Max Act: 5.1544. Min Act: -0.1700
Data Index: 2535612 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1544. Min Range: -5.1544
Max Act: 5.1231. Min Act: -0.1700
Data Index: 7382660 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1544. Min Range: -5.1544
Max Act: 5.0919. Min Act: -0.1700
Data Index: 5193355 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1544. Min Range: -5.1544
Max Act: 5.0919. Min Act: -0.1700
Data Index: 4828623 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1544. Min Range: -5.1544
Max Act: 5.0606. Min Act: -0.1700
Data Index: 1937746 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1544. Min Range: -5.1544
Max Act: 5.0606. Min Act: -0.1700
Data Index: 5148853 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1544. Min Range: -5.1544
Max Act: 5.0606. Min Act: -0.1700
Data Index: 2505960 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1544. Min Range: -5.1544
Max Act: 5.0294. Min Act: -0.1700
Data Index: 1048895 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1544. Min Range: -5.1544
Max Act: 5.0294. Min Act: -0.1700
Data Index: 6163212 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1544. Min Range: -5.1544
Max Act: 5.0294. Min Act: -0.1700
Data Index: 3079451 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1544. Min Range: -5.1544
Max Act: 5.0294. Min Act: -0.1700
Data Index: 8486956 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1544. Min Range: -5.1544
Max Act: 4.9981. Min Act: -0.1700
Data Index: 2681762 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1544. Min Range: -5.1544
Max Act: 4.9669. Min Act: -0.1700
Data Index: 2659588 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1544. Min Range: -5.1544
Max Act: 4.9981. Min Act: -0.1700
Data Index: 8451015 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1544. Min Range: -5.1544
Max Act: 4.9669. Min Act: -0.1700
Data Index: 1152918 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1544. Min Range: -5.1544
Max Act: 4.9981. Min Act: -0.1700
Data Index: 7671168 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1544. Min Range: -5.1544
Max Act: 4.9981. Min Act: -0.1700
Data Index: 1823736 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1544. Min Range: -5.1544
Max Act: 4.9669. Min Act: -0.1700
Data Index: 1316163 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1544. Min Range: -5.1544
Max Act: 4.9669. Min Act: -0.1700
Data Index: 917889 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #19