Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 795 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9993. Min Range: -5.9993
Max Act: 5.9993. Min Act: -0.1700
Data Index: 1900678 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9993. Min Range: -5.9993
Max Act: 5.9681. Min Act: -0.1700
Data Index: 5501338 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9993. Min Range: -5.9993
Max Act: 5.9368. Min Act: -0.1700
Data Index: 7282214 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9993. Min Range: -5.9993
Max Act: 5.9056. Min Act: -0.1700
Data Index: 6880826 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9993. Min Range: -5.9993
Max Act: 5.8743. Min Act: -0.1700
Data Index: 5459039 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9993. Min Range: -5.9993
Max Act: 5.8743. Min Act: -0.1700
Data Index: 170508 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9993. Min Range: -5.9993
Max Act: 5.8431. Min Act: -0.1700
Data Index: 8270094 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9993. Min Range: -5.9993
Max Act: 5.8743. Min Act: -0.1700
Data Index: 1776693 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9993. Min Range: -5.9993
Max Act: 5.8118. Min Act: -0.1700
Data Index: 62793 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9993. Min Range: -5.9993
Max Act: 5.7806. Min Act: -0.1700
Data Index: 1821104 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9993. Min Range: -5.9993
Max Act: 5.7181. Min Act: -0.1700
Data Index: 170522 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9993. Min Range: -5.9993
Max Act: 5.7181. Min Act: -0.1700
Data Index: 197464 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9993. Min Range: -5.9993
Max Act: 5.7493. Min Act: -0.1700
Data Index: 4439519 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9993. Min Range: -5.9993
Max Act: 5.7181. Min Act: -0.1700
Data Index: 4049508 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9993. Min Range: -5.9993
Max Act: 5.7181. Min Act: -0.1700
Data Index: 4415628 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9993. Min Range: -5.9993
Max Act: 5.6868. Min Act: -0.1700
Data Index: 1821103 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9993. Min Range: -5.9993
Max Act: 5.6556. Min Act: -0.1700
Data Index: 5708872 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9993. Min Range: -5.9993
Max Act: 5.6868. Min Act: -0.1700
Data Index: 170498 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9993. Min Range: -5.9993
Max Act: 5.6243. Min Act: -0.1700
Data Index: 8014789 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9993. Min Range: -5.9993
Max Act: 5.6243. Min Act: -0.1700
Data Index: 4752392 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #19