Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4539 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0642. Min Range: -8.0642
Max Act: 8.0642. Min Act: -0.1700
Data Index: 5345381 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0642. Min Range: -8.0642
Max Act: 8.0017. Min Act: -0.1700
Data Index: 3138783 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0642. Min Range: -8.0642
Max Act: 7.7829. Min Act: -0.1700
Data Index: 7052739 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0642. Min Range: -8.0642
Max Act: 7.7829. Min Act: -0.1700
Data Index: 4779705 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0642. Min Range: -8.0642
Max Act: 7.7829. Min Act: -0.1700
Data Index: 1988262 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0642. Min Range: -8.0642
Max Act: 7.7517. Min Act: -0.1700
Data Index: 4654731 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0642. Min Range: -8.0642
Max Act: 7.7204. Min Act: -0.1700
Data Index: 2191109 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0642. Min Range: -8.0642
Max Act: 7.7204. Min Act: -0.1700
Data Index: 7657403 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0642. Min Range: -8.0642
Max Act: 7.7204. Min Act: -0.1700
Data Index: 6998946 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0642. Min Range: -8.0642
Max Act: 7.7517. Min Act: -0.1700
Data Index: 2258104 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0642. Min Range: -8.0642
Max Act: 7.7204. Min Act: -0.1700
Data Index: 6834978 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0642. Min Range: -8.0642
Max Act: 7.6892. Min Act: -0.1700
Data Index: 3928443 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0642. Min Range: -8.0642
Max Act: 7.6579. Min Act: -0.1700
Data Index: 7892015 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0642. Min Range: -8.0642
Max Act: 7.6579. Min Act: -0.1700
Data Index: 2718968 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0642. Min Range: -8.0642
Max Act: 7.6579. Min Act: -0.1700
Data Index: 3489362 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0642. Min Range: -8.0642
Max Act: 7.6579. Min Act: -0.1700
Data Index: 2349150 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0642. Min Range: -8.0642
Max Act: 7.5954. Min Act: -0.1700
Data Index: 766641 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0642. Min Range: -8.0642
Max Act: 7.5642. Min Act: -0.1700
Data Index: 1789890 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0642. Min Range: -8.0642
Max Act: 7.6267. Min Act: -0.1700
Data Index: 917514 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0642. Min Range: -8.0642
Max Act: 7.5642. Min Act: -0.1700
Data Index: 1213517 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #19