Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 497 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3901. Min Range: -4.3901
Max Act: 4.3901. Min Act: -0.1700
Data Index: 5846234 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3901. Min Range: -4.3901
Max Act: 4.2963. Min Act: -0.1700
Data Index: 1990218 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3901. Min Range: -4.3901
Max Act: 4.2651. Min Act: -0.1700
Data Index: 5100822 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3901. Min Range: -4.3901
Max Act: 4.2338. Min Act: -0.1700
Data Index: 6484528 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3901. Min Range: -4.3901
Max Act: 4.0775. Min Act: -0.1700
Data Index: 1083599 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3901. Min Range: -4.3901
Max Act: 4.0775. Min Act: -0.1700
Data Index: 4881794 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3901. Min Range: -4.3901
Max Act: 4.0775. Min Act: -0.1700
Data Index: 6781298 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3901. Min Range: -4.3901
Max Act: 4.0775. Min Act: -0.1700
Data Index: 8594515 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3901. Min Range: -4.3901
Max Act: 4.0775. Min Act: -0.1700
Data Index: 1904978 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3901. Min Range: -4.3901
Max Act: 4.0775. Min Act: -0.1700
Data Index: 6870311 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3901. Min Range: -4.3901
Max Act: 4.0463. Min Act: -0.1700
Data Index: 7162538 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3901. Min Range: -4.3901
Max Act: 4.0463. Min Act: -0.1700
Data Index: 4346795 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3901. Min Range: -4.3901
Max Act: 4.0150. Min Act: -0.1700
Data Index: 2662275 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3901. Min Range: -4.3901
Max Act: 4.0150. Min Act: -0.1700
Data Index: 7790933 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3901. Min Range: -4.3901
Max Act: 3.9838. Min Act: -0.1700
Data Index: 6595634 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3901. Min Range: -4.3901
Max Act: 3.9838. Min Act: -0.1700
Data Index: 5482537 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3901. Min Range: -4.3901
Max Act: 3.9838. Min Act: -0.1700
Data Index: 3772629 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3901. Min Range: -4.3901
Max Act: 3.9838. Min Act: -0.1700
Data Index: 3828410 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3901. Min Range: -4.3901
Max Act: 3.9681. Min Act: -0.1700
Data Index: 2474162 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3901. Min Range: -4.3901
Max Act: 3.9525. Min Act: -0.1700
Data Index: 1515850 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19