Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3389 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3890. Min Range: -4.3890
Max Act: 4.3890. Min Act: -0.1700
Data Index: 860722 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3890. Min Range: -4.3890
Max Act: 4.3265. Min Act: -0.1700
Data Index: 2571938 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3890. Min Range: -4.3890
Max Act: 4.2640. Min Act: -0.1700
Data Index: 8344100 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3890. Min Range: -4.3890
Max Act: 4.2327. Min Act: -0.1700
Data Index: 5335815 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3890. Min Range: -4.3890
Max Act: 4.1702. Min Act: -0.1700
Data Index: 5559863 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3890. Min Range: -4.3890
Max Act: 4.1702. Min Act: -0.1700
Data Index: 1084067 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3890. Min Range: -4.3890
Max Act: 4.1390. Min Act: -0.1700
Data Index: 7545004 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3890. Min Range: -4.3890
Max Act: 4.1390. Min Act: -0.1700
Data Index: 8147616 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3890. Min Range: -4.3890
Max Act: 4.1390. Min Act: -0.1700
Data Index: 6812220 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3890. Min Range: -4.3890
Max Act: 4.1077. Min Act: -0.1700
Data Index: 6086204 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3890. Min Range: -4.3890
Max Act: 4.1390. Min Act: -0.1700
Data Index: 2641887 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3890. Min Range: -4.3890
Max Act: 4.1390. Min Act: -0.1700
Data Index: 233881 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3890. Min Range: -4.3890
Max Act: 4.1077. Min Act: -0.1700
Data Index: 6679453 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3890. Min Range: -4.3890
Max Act: 4.1077. Min Act: -0.1700
Data Index: 6933175 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3890. Min Range: -4.3890
Max Act: 4.1077. Min Act: -0.1700
Data Index: 3266122 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3890. Min Range: -4.3890
Max Act: 4.1077. Min Act: -0.1700
Data Index: 7210356 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3890. Min Range: -4.3890
Max Act: 4.1077. Min Act: -0.1700
Data Index: 4016678 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3890. Min Range: -4.3890
Max Act: 4.1077. Min Act: -0.1700
Data Index: 3047558 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3890. Min Range: -4.3890
Max Act: 4.0764. Min Act: -0.1700
Data Index: 6858370 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3890. Min Range: -4.3890
Max Act: 4.0764. Min Act: -0.1700
Data Index: 7417602 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #19