Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4268 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4517. Min Range: -6.4517
Max Act: 6.4517. Min Act: -0.1700
Data Index: 4347847 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4517. Min Range: -6.4517
Max Act: 6.3580. Min Act: -0.1700
Data Index: 7295350 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4517. Min Range: -6.4517
Max Act: 6.3580. Min Act: -0.1700
Data Index: 6771057 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4517. Min Range: -6.4517
Max Act: 6.3580. Min Act: -0.1700
Data Index: 3038292 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4517. Min Range: -6.4517
Max Act: 6.3267. Min Act: -0.1700
Data Index: 6343180 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4517. Min Range: -6.4517
Max Act: 6.3267. Min Act: -0.1700
Data Index: 118692 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4517. Min Range: -6.4517
Max Act: 6.3267. Min Act: -0.1700
Data Index: 8118099 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4517. Min Range: -6.4517
Max Act: 6.2642. Min Act: -0.1700
Data Index: 3407681 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4517. Min Range: -6.4517
Max Act: 6.2017. Min Act: -0.1700
Data Index: 3675190 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4517. Min Range: -6.4517
Max Act: 6.1705. Min Act: -0.1700
Data Index: 487243 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4517. Min Range: -6.4517
Max Act: 6.1705. Min Act: -0.1700
Data Index: 1053846 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4517. Min Range: -6.4517
Max Act: 6.1392. Min Act: -0.1700
Data Index: 6641195 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4517. Min Range: -6.4517
Max Act: 6.1705. Min Act: -0.1700
Data Index: 7782559 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4517. Min Range: -6.4517
Max Act: 6.1080. Min Act: -0.1700
Data Index: 2566605 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4517. Min Range: -6.4517
Max Act: 6.0767. Min Act: -0.1700
Data Index: 5253969 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4517. Min Range: -6.4517
Max Act: 6.0142. Min Act: -0.1700
Data Index: 8416130 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4517. Min Range: -6.4517
Max Act: 6.0455. Min Act: -0.1700
Data Index: 5343017 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4517. Min Range: -6.4517
Max Act: 6.0142. Min Act: -0.1700
Data Index: 2565810 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4517. Min Range: -6.4517
Max Act: 5.9830. Min Act: -0.1700
Data Index: 2497548 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4517. Min Range: -6.4517
Max Act: 5.9830. Min Act: -0.1700
Data Index: 6188562 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #19