Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5171 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1747. Min Range: -3.1747
Max Act: 3.1747. Min Act: -0.1700
Data Index: 4018009 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1747. Min Range: -3.1747
Max Act: 2.9063. Min Act: -0.1700
Data Index: 6181858 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1747. Min Range: -3.1747
Max Act: 2.8587. Min Act: -0.1700
Data Index: 629332 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1747. Min Range: -3.1747
Max Act: 2.7950. Min Act: -0.1700
Data Index: 167861 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1747. Min Range: -3.1747
Max Act: 2.8110. Min Act: -0.1700
Data Index: 2515124 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1747. Min Range: -3.1747
Max Act: 2.7791. Min Act: -0.1700
Data Index: 6232901 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1747. Min Range: -3.1747
Max Act: 2.7791. Min Act: -0.1700
Data Index: 1031057 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1747. Min Range: -3.1747
Max Act: 2.7791. Min Act: -0.1700
Data Index: 6069964 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1747. Min Range: -3.1747
Max Act: 2.7472. Min Act: -0.1700
Data Index: 4650796 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1747. Min Range: -3.1747
Max Act: 2.7632. Min Act: -0.1700
Data Index: 4561202 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1747. Min Range: -3.1747
Max Act: 2.7472. Min Act: -0.1700
Data Index: 7230246 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1747. Min Range: -3.1747
Max Act: 2.7472. Min Act: -0.1700
Data Index: 6152489 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1747. Min Range: -3.1747
Max Act: 2.7312. Min Act: -0.1700
Data Index: 7422938 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1747. Min Range: -3.1747
Max Act: 2.7472. Min Act: -0.1700
Data Index: 3720938 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1747. Min Range: -3.1747
Max Act: 2.7312. Min Act: -0.1700
Data Index: 4025148 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1747. Min Range: -3.1747
Max Act: 2.7153. Min Act: -0.1700
Data Index: 4007842 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1747. Min Range: -3.1747
Max Act: 2.6993. Min Act: -0.1700
Data Index: 4164239 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1747. Min Range: -3.1747
Max Act: 2.6993. Min Act: -0.1700
Data Index: 3438507 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1747. Min Range: -3.1747
Max Act: 2.6833. Min Act: -0.1700
Data Index: 6928304 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1747. Min Range: -3.1747
Max Act: 2.6672. Min Act: -0.1700
Data Index: 7120300 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #19