Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3764 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5640. Min Range: -5.5640
Max Act: 5.5640. Min Act: -0.1700
Data Index: 1331161 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5640. Min Range: -5.5640
Max Act: 5.4703. Min Act: -0.1700
Data Index: 6975613 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5640. Min Range: -5.5640
Max Act: 5.4703. Min Act: -0.1700
Data Index: 1079374 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5640. Min Range: -5.5640
Max Act: 5.4390. Min Act: -0.1700
Data Index: 7342086 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5640. Min Range: -5.5640
Max Act: 5.4390. Min Act: -0.1700
Data Index: 6668895 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5640. Min Range: -5.5640
Max Act: 5.4078. Min Act: -0.1700
Data Index: 5421581 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5640. Min Range: -5.5640
Max Act: 5.4078. Min Act: -0.1700
Data Index: 3013290 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5640. Min Range: -5.5640
Max Act: 5.4078. Min Act: -0.1700
Data Index: 1469280 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5640. Min Range: -5.5640
Max Act: 5.4078. Min Act: -0.1700
Data Index: 1542556 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5640. Min Range: -5.5640
Max Act: 5.4078. Min Act: -0.1700
Data Index: 8457895 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5640. Min Range: -5.5640
Max Act: 5.3765. Min Act: -0.1700
Data Index: 2307029 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5640. Min Range: -5.5640
Max Act: 5.3765. Min Act: -0.1700
Data Index: 6374971 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5640. Min Range: -5.5640
Max Act: 5.3765. Min Act: -0.1700
Data Index: 6313613 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5640. Min Range: -5.5640
Max Act: 5.4078. Min Act: -0.1700
Data Index: 1413695 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5640. Min Range: -5.5640
Max Act: 5.3765. Min Act: -0.1700
Data Index: 944066 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5640. Min Range: -5.5640
Max Act: 5.3765. Min Act: -0.1700
Data Index: 8383731 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5640. Min Range: -5.5640
Max Act: 5.3765. Min Act: -0.1700
Data Index: 918896 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5640. Min Range: -5.5640
Max Act: 5.3765. Min Act: -0.1700
Data Index: 8369306 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5640. Min Range: -5.5640
Max Act: 5.3765. Min Act: -0.1700
Data Index: 3426575 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5640. Min Range: -5.5640
Max Act: 5.3453. Min Act: -0.1700
Data Index: 6770362 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #19