Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2587 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7757. Min Range: -9.7757
Max Act: 9.7757. Min Act: -0.1700
Data Index: 3358186 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7757. Min Range: -9.7757
Max Act: 9.4632. Min Act: -0.1700
Data Index: 8649715 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7757. Min Range: -9.7757
Max Act: 9.4007. Min Act: -0.1700
Data Index: 5873537 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7757. Min Range: -9.7757
Max Act: 9.3382. Min Act: -0.1700
Data Index: 2748549 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7757. Min Range: -9.7757
Max Act: 9.3382. Min Act: -0.1700
Data Index: 4708378 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7757. Min Range: -9.7757
Max Act: 9.2757. Min Act: -0.1700
Data Index: 3327219 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7757. Min Range: -9.7757
Max Act: 9.2757. Min Act: -0.1700
Data Index: 4091617 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7757. Min Range: -9.7757
Max Act: 9.2132. Min Act: -0.1700
Data Index: 6315228 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7757. Min Range: -9.7757
Max Act: 9.2132. Min Act: -0.1700
Data Index: 4368005 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7757. Min Range: -9.7757
Max Act: 9.1507. Min Act: -0.1700
Data Index: 16703 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7757. Min Range: -9.7757
Max Act: 9.1507. Min Act: -0.1700
Data Index: 642552 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7757. Min Range: -9.7757
Max Act: 9.1507. Min Act: -0.1700
Data Index: 3712496 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7757. Min Range: -9.7757
Max Act: 9.1507. Min Act: -0.1700
Data Index: 1254913 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7757. Min Range: -9.7757
Max Act: 9.0882. Min Act: -0.1700
Data Index: 817270 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7757. Min Range: -9.7757
Max Act: 9.0257. Min Act: -0.1700
Data Index: 8766181 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7757. Min Range: -9.7757
Max Act: 9.0257. Min Act: -0.1700
Data Index: 572647 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7757. Min Range: -9.7757
Max Act: 9.0257. Min Act: -0.1700
Data Index: 1637946 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7757. Min Range: -9.7757
Max Act: 9.0257. Min Act: -0.1700
Data Index: 1425243 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7757. Min Range: -9.7757
Max Act: 9.0257. Min Act: -0.1700
Data Index: 3452754 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7757. Min Range: -9.7757
Max Act: 8.9632. Min Act: -0.1700
Data Index: 4079565 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #19