Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3529 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2797. Min Range: -3.2797
Max Act: 3.2797. Min Act: -0.1700
Data Index: 2484095 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2797. Min Range: -3.2797
Max Act: 3.2640. Min Act: -0.1700
Data Index: 1269878 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2797. Min Range: -3.2797
Max Act: 3.2011. Min Act: -0.1700
Data Index: 7025415 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2797. Min Range: -3.2797
Max Act: 3.1854. Min Act: -0.1700
Data Index: 1467519 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2797. Min Range: -3.2797
Max Act: 3.1854. Min Act: -0.1700
Data Index: 5185716 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2797. Min Range: -3.2797
Max Act: 3.1696. Min Act: -0.1700
Data Index: 1165256 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2797. Min Range: -3.2797
Max Act: 3.1696. Min Act: -0.1700
Data Index: 4366621 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2797. Min Range: -3.2797
Max Act: 3.1539. Min Act: -0.1700
Data Index: 7097930 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2797. Min Range: -3.2797
Max Act: 3.1224. Min Act: -0.1700
Data Index: 6461605 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2797. Min Range: -3.2797
Max Act: 3.1381. Min Act: -0.1700
Data Index: 7117960 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2797. Min Range: -3.2797
Max Act: 3.1381. Min Act: -0.1700
Data Index: 3696515 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2797. Min Range: -3.2797
Max Act: 3.1381. Min Act: -0.1700
Data Index: 7537261 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2797. Min Range: -3.2797
Max Act: 3.1381. Min Act: -0.1700
Data Index: 7243992 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2797. Min Range: -3.2797
Max Act: 3.1224. Min Act: -0.1700
Data Index: 6874500 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2797. Min Range: -3.2797
Max Act: 3.1224. Min Act: -0.1700
Data Index: 2388065 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2797. Min Range: -3.2797
Max Act: 3.1224. Min Act: -0.1700
Data Index: 6380352 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2797. Min Range: -3.2797
Max Act: 3.1224. Min Act: -0.1700
Data Index: 2970536 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2797. Min Range: -3.2797
Max Act: 3.1224. Min Act: -0.1700
Data Index: 1531912 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2797. Min Range: -3.2797
Max Act: 3.1224. Min Act: -0.1700
Data Index: 2868937 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2797. Min Range: -3.2797
Max Act: 3.1224. Min Act: -0.1700
Data Index: 416051 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #19