Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5970 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1619. Min Range: -5.1619
Max Act: 5.1619. Min Act: -0.1700
Data Index: 5434494 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1619. Min Range: -5.1619
Max Act: 5.1306. Min Act: -0.1700
Data Index: 195888 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1619. Min Range: -5.1619
Max Act: 5.0681. Min Act: -0.1700
Data Index: 5661896 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1619. Min Range: -5.1619
Max Act: 5.0369. Min Act: -0.1700
Data Index: 7508585 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1619. Min Range: -5.1619
Max Act: 5.0369. Min Act: -0.1700
Data Index: 7613923 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1619. Min Range: -5.1619
Max Act: 4.9744. Min Act: -0.1700
Data Index: 3975451 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1619. Min Range: -5.1619
Max Act: 5.0056. Min Act: -0.1700
Data Index: 6396307 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1619. Min Range: -5.1619
Max Act: 4.9744. Min Act: -0.1700
Data Index: 3253727 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1619. Min Range: -5.1619
Max Act: 4.9119. Min Act: -0.1700
Data Index: 5863944 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1619. Min Range: -5.1619
Max Act: 4.9119. Min Act: -0.1700
Data Index: 266062 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1619. Min Range: -5.1619
Max Act: 4.9119. Min Act: -0.1700
Data Index: 6388158 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1619. Min Range: -5.1619
Max Act: 4.9119. Min Act: -0.1700
Data Index: 1817750 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1619. Min Range: -5.1619
Max Act: 4.9119. Min Act: -0.1700
Data Index: 5661894 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1619. Min Range: -5.1619
Max Act: 4.8806. Min Act: -0.1700
Data Index: 3489413 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1619. Min Range: -5.1619
Max Act: 4.8806. Min Act: -0.1700
Data Index: 8815655 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1619. Min Range: -5.1619
Max Act: 4.8806. Min Act: -0.1700
Data Index: 8116876 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1619. Min Range: -5.1619
Max Act: 4.8806. Min Act: -0.1700
Data Index: 5338851 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1619. Min Range: -5.1619
Max Act: 4.8806. Min Act: -0.1700
Data Index: 1717742 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1619. Min Range: -5.1619
Max Act: 4.8806. Min Act: -0.1700
Data Index: 1344411 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1619. Min Range: -5.1619
Max Act: 4.8494. Min Act: -0.1700
Data Index: 1817751 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #19