Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4649 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7821. Min Range: -9.7821
Max Act: 9.7821. Min Act: -0.1700
Data Index: 4088264 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7821. Min Range: -9.7821
Max Act: 9.6571. Min Act: -0.1700
Data Index: 4467842 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7821. Min Range: -9.7821
Max Act: 9.4696. Min Act: -0.1700
Data Index: 2416634 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7821. Min Range: -9.7821
Max Act: 9.2196. Min Act: -0.1700
Data Index: 7806442 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7821. Min Range: -9.7821
Max Act: 9.0946. Min Act: -0.1700
Data Index: 4619063 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7821. Min Range: -9.7821
Max Act: 9.0946. Min Act: -0.1700
Data Index: 6954592 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7821. Min Range: -9.7821
Max Act: 9.0946. Min Act: -0.1700
Data Index: 992952 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7821. Min Range: -9.7821
Max Act: 8.9696. Min Act: -0.1700
Data Index: 4410795 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7821. Min Range: -9.7821
Max Act: 8.9696. Min Act: -0.1700
Data Index: 4180557 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7821. Min Range: -9.7821
Max Act: 8.9696. Min Act: -0.1700
Data Index: 1709571 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7821. Min Range: -9.7821
Max Act: 8.9696. Min Act: -0.1700
Data Index: 4057044 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7821. Min Range: -9.7821
Max Act: 8.9696. Min Act: -0.1700
Data Index: 6146800 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7821. Min Range: -9.7821
Max Act: 9.0321. Min Act: -0.1700
Data Index: 141137 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7821. Min Range: -9.7821
Max Act: 8.9696. Min Act: -0.1700
Data Index: 4257051 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7821. Min Range: -9.7821
Max Act: 8.8446. Min Act: -0.1700
Data Index: 3341014 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7821. Min Range: -9.7821
Max Act: 8.9071. Min Act: -0.1700
Data Index: 8582365 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7821. Min Range: -9.7821
Max Act: 8.9071. Min Act: -0.1700
Data Index: 4490709 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7821. Min Range: -9.7821
Max Act: 8.9071. Min Act: -0.1700
Data Index: 4227576 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7821. Min Range: -9.7821
Max Act: 8.8446. Min Act: -0.1700
Data Index: 4361575 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7821. Min Range: -9.7821
Max Act: 8.8446. Min Act: -0.1700
Data Index: 2055892 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #19