Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2649 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.8558. Min Range: -7.8558
Max Act: 7.8558. Min Act: -0.1700
Data Index: 1339345 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8558. Min Range: -7.8558
Max Act: 7.8245. Min Act: -0.1700
Data Index: 299285 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8558. Min Range: -7.8558
Max Act: 7.6683. Min Act: -0.1700
Data Index: 6684366 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8558. Min Range: -7.8558
Max Act: 7.6370. Min Act: -0.1700
Data Index: 4967755 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8558. Min Range: -7.8558
Max Act: 7.5433. Min Act: -0.1700
Data Index: 1405997 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8558. Min Range: -7.8558
Max Act: 7.5433. Min Act: -0.1700
Data Index: 3343987 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8558. Min Range: -7.8558
Max Act: 7.5433. Min Act: -0.1700
Data Index: 5936932 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8558. Min Range: -7.8558
Max Act: 7.5120. Min Act: -0.1700
Data Index: 6821909 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8558. Min Range: -7.8558
Max Act: 7.5120. Min Act: -0.1700
Data Index: 8431589 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8558. Min Range: -7.8558
Max Act: 7.4808. Min Act: -0.1700
Data Index: 4800536 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8558. Min Range: -7.8558
Max Act: 7.5120. Min Act: -0.1700
Data Index: 1337635 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8558. Min Range: -7.8558
Max Act: 7.3870. Min Act: -0.1700
Data Index: 1093265 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8558. Min Range: -7.8558
Max Act: 7.3870. Min Act: -0.1700
Data Index: 7390441 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8558. Min Range: -7.8558
Max Act: 7.3870. Min Act: -0.1700
Data Index: 2282196 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8558. Min Range: -7.8558
Max Act: 7.3870. Min Act: -0.1700
Data Index: 6542113 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8558. Min Range: -7.8558
Max Act: 7.4183. Min Act: -0.1700
Data Index: 2788435 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8558. Min Range: -7.8558
Max Act: 7.3558. Min Act: -0.1700
Data Index: 2021801 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8558. Min Range: -7.8558
Max Act: 7.3245. Min Act: -0.1700
Data Index: 5095461 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8558. Min Range: -7.8558
Max Act: 7.3558. Min Act: -0.1700
Data Index: 6154710 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8558. Min Range: -7.8558
Max Act: 7.2620. Min Act: -0.1700
Data Index: 3362485 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #19