Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5198 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.9689. Min Range: -10.9689
Max Act: 10.9689. Min Act: -0.1700
Data Index: 8099494 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.9689. Min Range: -10.9689
Max Act: 10.7814. Min Act: -0.1700
Data Index: 378218 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.9689. Min Range: -10.9689
Max Act: 10.2814. Min Act: -0.1700
Data Index: 4704865 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.9689. Min Range: -10.9689
Max Act: 10.0314. Min Act: -0.1700
Data Index: 3376422 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.9689. Min Range: -10.9689
Max Act: 10.0314. Min Act: -0.1700
Data Index: 7788483 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.9689. Min Range: -10.9689
Max Act: 10.0314. Min Act: -0.1700
Data Index: 5142921 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.9689. Min Range: -10.9689
Max Act: 9.9689. Min Act: -0.1700
Data Index: 7788484 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.9689. Min Range: -10.9689
Max Act: 10.0314. Min Act: -0.1700
Data Index: 5839780 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.9689. Min Range: -10.9689
Max Act: 9.9689. Min Act: -0.1700
Data Index: 7845387 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.9689. Min Range: -10.9689
Max Act: 9.9064. Min Act: -0.1700
Data Index: 8612374 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.9689. Min Range: -10.9689
Max Act: 9.8439. Min Act: -0.1700
Data Index: 5033392 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.9689. Min Range: -10.9689
Max Act: 9.8439. Min Act: -0.1700
Data Index: 6610010 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.9689. Min Range: -10.9689
Max Act: 9.7814. Min Act: -0.1700
Data Index: 1562678 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.9689. Min Range: -10.9689
Max Act: 9.7189. Min Act: -0.1700
Data Index: 8022708 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.9689. Min Range: -10.9689
Max Act: 9.7814. Min Act: -0.1700
Data Index: 8739342 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.9689. Min Range: -10.9689
Max Act: 9.7814. Min Act: -0.1700
Data Index: 3429688 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.9689. Min Range: -10.9689
Max Act: 9.7814. Min Act: -0.1700
Data Index: 8281598 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.9689. Min Range: -10.9689
Max Act: 9.7814. Min Act: -0.1700
Data Index: 8274984 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.9689. Min Range: -10.9689
Max Act: 9.7189. Min Act: -0.1700
Data Index: 538027 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.9689. Min Range: -10.9689
Max Act: 9.7189. Min Act: -0.1700
Data Index: 4377013 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #19