Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3317 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3453. Min Range: -5.3453
Max Act: 5.3453. Min Act: -0.1700
Data Index: 2440653 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3453. Min Range: -5.3453
Max Act: 5.2515. Min Act: -0.1700
Data Index: 960758 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3453. Min Range: -5.3453
Max Act: 5.1890. Min Act: -0.1700
Data Index: 975953 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3453. Min Range: -5.3453
Max Act: 5.1890. Min Act: -0.1700
Data Index: 7362772 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3453. Min Range: -5.3453
Max Act: 5.1890. Min Act: -0.1700
Data Index: 1048098 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3453. Min Range: -5.3453
Max Act: 5.1578. Min Act: -0.1700
Data Index: 5635723 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3453. Min Range: -5.3453
Max Act: 5.1578. Min Act: -0.1700
Data Index: 7627826 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3453. Min Range: -5.3453
Max Act: 5.0953. Min Act: -0.1700
Data Index: 8314096 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3453. Min Range: -5.3453
Max Act: 5.0640. Min Act: -0.1700
Data Index: 3930059 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3453. Min Range: -5.3453
Max Act: 5.0640. Min Act: -0.1700
Data Index: 2981933 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3453. Min Range: -5.3453
Max Act: 5.0328. Min Act: -0.1700
Data Index: 7781565 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3453. Min Range: -5.3453
Max Act: 5.0328. Min Act: -0.1700
Data Index: 5543319 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3453. Min Range: -5.3453
Max Act: 5.0328. Min Act: -0.1700
Data Index: 2951231 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3453. Min Range: -5.3453
Max Act: 5.0328. Min Act: -0.1700
Data Index: 6017672 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3453. Min Range: -5.3453
Max Act: 5.0015. Min Act: -0.1700
Data Index: 5938417 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3453. Min Range: -5.3453
Max Act: 5.0015. Min Act: -0.1700
Data Index: 7622212 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3453. Min Range: -5.3453
Max Act: 4.9703. Min Act: -0.1700
Data Index: 2703957 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3453. Min Range: -5.3453
Max Act: 4.9390. Min Act: -0.1700
Data Index: 7315995 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3453. Min Range: -5.3453
Max Act: 4.9390. Min Act: -0.1700
Data Index: 50603 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3453. Min Range: -5.3453
Max Act: 4.9078. Min Act: -0.1700
Data Index: 7021393 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #19